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

    Neuronpedia

    INDEX
    Explanations

    specific numerical patterns or values

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

    Non-English (foreign) words

    np_acts-logits-general · gemini-2.0-flash

    code file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rália
    -0.57
    ulties
    -0.54
    PyObject
    -0.52
     dabei
    -0.49
    ²/
    -0.49
    clearInterval
    -0.44
     TType
    -0.42
    Répondre
    -0.42
     Pencil
    -0.42
    assies
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.82
     مرئيه
    0.73
    انيف
    0.71
    Demografia
    0.71
    Portail
    0.71
    expandindo
    0.64
     beginnetje
    0.63
     مشين
    0.62
    tonsoft
    0.61
    findpost
    0.61
    Act Density 0.022%

    No Known Activations