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

    Neuronpedia

    INDEX
    Explanations

    male

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     멀
    -0.07
     金
    -0.07
     tzv
    -0.06
    _last
    -0.06
    佐
    -0.06
    -dollar
    -0.06
     euro
    -0.06
     quienes
    -0.06
    Mixin
    -0.06
     हत
    -0.06
    POSITIVE LOGITS
    мотря
    0.07
    戻
    0.07
    lius
    0.06
     citing
    0.06
     pipelines
    0.06
    Crystal
    0.06
    нений
    0.06
     tussen
    0.06
     ingresar
    0.06
    _prim
    0.06
    Act Density 0.010%

    No Known Activations