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

    Neuronpedia

    INDEX
    Explanations

    stat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    长相
    -0.08
    _android
    -0.08
    _dense
    -0.07
    หญ
    -0.07
     punish
    -0.07
    .Location
    -0.07
     cô
    -0.07
     Only
    -0.07
     Tenant
    -0.07
    _DOM
    -0.06
    POSITIVE LOGITS
    Stat
    0.08
    ита
    0.08
    ylation
    0.07
    uales
    0.07
     Stat
    0.07
    	stat
    0.07
    prob
    0.07
     tal
    0.07
    㟁
    0.07
    kee
    0.07
    Act Density 0.008%

    No Known Activations