Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific instances of sentences and structures that indicate descriptions or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spatial relationships or proximity

    np_acts-logits-general · gemini-2.0-flash

    end of sentence or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.79
     الرياضيه
    -0.68
    енча
    -0.67
     ujednoznacz
    -0.65
    Tazama
    -0.64
    Демографія
    -0.61
    reportWebVitals
    -0.60
     additive
    -0.60
     Мексичка
    -0.60
    ItemLayout
    -0.60
    POSITIVE LOGITS
     surrounding
    0.71
     underneath
    0.66
     surrounds
    0.61
     surrounded
    0.61
     beneath
    0.59
     adjacent
    0.57
     nearby
    0.56
     beside
    0.52
    Adjacent
    0.52
     flanked
    0.51
    Act Density 0.434%

    No Known Activations