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

    Neuronpedia

    INDEX
    Explanations

    references to specific researchers or studies in a scientific context

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

    names and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.77
     resourceCulture
    -0.77
    toHaveBeenCalled
    -0.68
    UserScript
    -0.63
    Castell
    -0.61
     <<<<<<<<<<<<<<
    -0.59
    createServer
    -0.59
    pallet
    -0.58
    ArgumentParser
    -0.57
    awtextra
    -0.57
    POSITIVE LOGITS
     Irán
    0.54
     aikaa
    0.50
     dictadura
    0.49
     katholischen
    0.45
     krig
    0.45
     pierna
    0.43
     cierta
    0.43
     Ordem
    0.43
     semanal
    0.43
    guenos
    0.43
    Act Density 0.423%

    No Known Activations