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

    Neuronpedia

    INDEX
    Explanations

    .io

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ьми
    -0.07
    -side
    -0.06
    /comment
    -0.06
     etkin
    -0.06
    _mass
    -0.06
    vable
    -0.06
    dom
    -0.06
     contractor
    -0.06
     governments
    -0.06
    .Character
    -0.06
    POSITIVE LOGITS
    .isPlaying
    0.07
    UDP
    0.07
    (balance
    0.06
    167
    0.06
     Wayne
    0.06
    arsing
    0.06
    January
    0.06
    (lr
    0.06
    exampleModal
    0.06
     sell
    0.06
    Act Density 0.002%

    No Known Activations