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

    Neuronpedia

    INDEX
    Explanations

    ang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acum
    -0.06
    eos
    -0.06
    992
    -0.06
    secret
    -0.06
    Init
    -0.06
    _dense
    -0.06
    ded
    -0.06
     Bez
    -0.06
     subsidiary
    -0.06
    Feature
    -0.06
    POSITIVE LOGITS
    ourn
    0.09
    ，那
    0.07
     witches
    0.07
     landsc
    0.06
     Eastern
    0.06
    angu
    0.06
    lang
    0.06
    /status
    0.06
    .GO
    0.06
    .Contains
    0.06
    Act Density 0.001%

    No Known Activations