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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excuses
    -0.07
    پ
    -0.07
    _sphere
    -0.07
    алу
    -0.07
    createUrl
    -0.07
    =h
    -0.07
     breed
    -0.06
    Be
    -0.06
    ских
    -0.06
    (bucket
    -0.06
    POSITIVE LOGITS
     jud
    0.08
    ................................
    0.06
     CCT
    0.06
    ／
    0.06
     Jos
    0.06
    .ind
    0.06
     Noise
    0.06
    James
    0.06
    ................................
    0.06
    .↵
    0.06
    Act Density 0.333%

    No Known Activations