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

    Neuronpedia

    INDEX
    Explanations

    common words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dtype
    -0.07
     Crack
    -0.07
    kanı
    -0.06
    .room
    -0.06
    Deprecated
    -0.06
     iterations
    -0.06
     ساختمان
    -0.06
     deprecated
    -0.06
     QFile
    -0.06
    .dev
    -0.06
    POSITIVE LOGITS
    派
    0.07
     allocating
    0.06
     armá
    0.06
    omo
    0.06
    猫
    0.06
     whatsoever
    0.06
     Edgar
    0.06
     хозяй
    0.06
    keletal
    0.06
    ffi
    0.06
    Act Density 0.000%

    No Known Activations