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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嫌
    -0.06
    _ORIENTATION
    -0.06
     обол
    -0.06
     passenger
    -0.06
     videos
    -0.06
     llama
    -0.06
     scandals
    -0.06
     Comprehensive
    -0.06
    .sprites
    -0.06
    ПО
    -0.06
    POSITIVE LOGITS
    τικής
    0.07
    egal
    0.07
    /w
    0.07
     uch
    0.07
     say
    0.06
    .calculate
    0.06
    .Many
    0.06
    Letters
    0.06
    もり
    0.06
    oub
    0.06
    Act Density 0.049%

    No Known Activations