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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行人
    -0.07
    Power
    -0.07
    ":"",↵
    -0.07
     Torch
    -0.06
    UIApplicationDelegate
    -0.06
     seized
    -0.06
    И
    -0.06
    从小就
    -0.06
     perhaps
    -0.06
    Luke
    -0.06
    POSITIVE LOGITS
     CET
    0.07
    cams
    0.07
    .datab
    0.07
     cwd
    0.07
    _LAT
    0.07
    ynchron
    0.07
    -art
    0.07
     [...
    0.07
    _CUSTOMER
    0.07
    FD
    0.06
    Act Density 0.003%

    No Known Activations