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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bare
    -0.06
    /false
    -0.06
     Kis
    -0.06
     xin
    -0.06
    "path
    -0.06
     Ankara
    -0.06
    ’T
    -0.06
     Button
    -0.06
    _recipe
    -0.06
    ’t
    -0.06
    POSITIVE LOGITS
     правильно
    0.07
    ož
    0.07
    periments
    0.07
    ordinal
    0.06
    ancellable
    0.06
    Large
    0.06
    _SY
    0.06
    елич
    0.06
    �에
    0.06
    _structure
    0.06
    Act Density 0.006%

    No Known Activations