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

    Neuronpedia

    INDEX
    Explanations

    academic/research texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Birthday
    -0.07
     shouldn
    -0.06
     seller
    -0.06
     denně
    -0.06
     sqlalchemy
    -0.06
     grew
    -0.06
    。あ
    -0.06
     Academic
    -0.06
    らし
    -0.06
    Question
    -0.06
    POSITIVE LOGITS
    mo
    0.07
    :@
    0.07
     가능한
    0.07
    textTheme
    0.07
    ILER
    0.06
    ･
    0.06
    IOException
    0.06
    θεια
    0.06
    OF
    0.06
     ساخت
    0.06
    Act Density 0.562%

    No Known Activations