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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     голод
    -0.07
    頂
    -0.07
    (enable
    -0.06
     squarely
    -0.06
    lač
    -0.06
    _density
    -0.06
    -dot
    -0.06
     อำ
    -0.06
     Corporation
    -0.06
    QQ
    -0.06
    POSITIVE LOGITS
    ono
    0.07
    şi
    0.06
     nt
    0.06
    ONO
    0.06
    te
    0.06
    (il
    0.06
     Santo
    0.06
     fleets
    0.06
     […]...↵
    0.06
    272
    0.06
    Act Density 0.000%

    No Known Activations