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

    Neuronpedia

    INDEX
    Explanations

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gson
    -0.07
     anomaly
    -0.07
    .override
    -0.07
     Employ
    -0.06
    _Db
    -0.06
    _eps
    -0.06
    anny
    -0.06
     Eh
    -0.06
    _intro
    -0.06
    kar
    -0.06
    POSITIVE LOGITS
    рич
    0.06
    =add
    0.06
    acağ
    0.05
     detta
    0.05
     Hayes
    0.05
     живот
    0.05
    COVERY
    0.05
    _dense
    0.05
    /animate
    0.05
     ordering
    0.05
    Act Density 0.000%

    No Known Activations