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

    Neuronpedia

    INDEX
    Explanations

    esModule

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     time
    -0.07
    "user
    -0.07
     FS
    -0.07
    +"'
    -0.07
    )//
    -0.07
     %
    -0.06
     Managers
    -0.06
    =>
    -0.06
    ;d
    -0.06
    case
    -0.06
    POSITIVE LOGITS
    ktör
    0.09
    computed
    0.08
    _route
    0.07
    轭
    0.07
    פוט
    0.07
     abandoning
    0.07
     Brotherhood
    0.07
    必不可
    0.07
     Bronx
    0.07
    戆
    0.07
    Act Density 0.000%

    No Known Activations