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

    Neuronpedia

    INDEX
    Explanations

    activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sz
    -0.08
     elt
    -0.07
     sido
    -0.07
    芷
    -0.07
    ialized
    -0.07
    ¡
    -0.07
    api
    -0.07
    .must
    -0.07
    .dup
    -0.07
     emission
    -0.07
    POSITIVE LOGITS
    _IMAGE
    0.06
    ネ
    0.06
     Two
    0.06
    民政局
    0.06
    rea
    0.06
    (force
    0.06
     Democracy
    0.06
     reproduced
    0.06
    гон
    0.06
    cale
    0.06
    Act Density 0.021%

    No Known Activations