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

    Neuronpedia

    INDEX
    Explanations

    sister

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llevar
    -0.07
    喑
    -0.07
    為了
    -0.07
    exion
    -0.07
    长大
    -0.06
     Sexe
    -0.06
     eer
    -0.06
    InputLabel
    -0.06
    װ
    -0.06
    몀
    -0.06
    POSITIVE LOGITS
    _hub
    0.08
    _STRUCT
    0.08
    PID
    0.08
    PROCESS
    0.07
     Advisors
    0.07
     dilation
    0.07
    _Property
    0.07
    _Form
    0.07
    authorize
    0.07
     diligence
    0.07
    Act Density 0.016%

    No Known Activations