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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vf
    -0.07
    -ни
    -0.06
    ))+
    -0.06
     Pf
    -0.06
     pk
    -0.06
    //*
    -0.06
     manages
    -0.06
     maz
    -0.06
     zast
    -0.06
     해
    -0.06
    POSITIVE LOGITS
     شهری
    0.08
    idential
    0.07
     initView
    0.07
    .ListView
    0.06
    YELLOW
    0.06
    archives
    0.06
     aktuální
    0.06
    ätze
    0.06
    iglia
    0.06
     شخص
    0.06
    Act Density 0.021%

    No Known Activations