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

    Neuronpedia

    INDEX
    Explanations

    returns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sense
    -0.08
    ƒ
    -0.07
     आदम
    -0.07
    età
    -0.06
    _LEVEL
    -0.06
    zek
    -0.06
    Дж
    -0.06
    Ñ
    -0.06
     конкур
    -0.06
    math
    -0.06
    POSITIVE LOGITS
    returns
    0.08
     undis
    0.07
     ký
    0.06
     bec
    0.06
    τους
    0.06
     ομά
    0.06
    atti
    0.06
    .Wh
    0.06
    eterangan
    0.06
    (ab
    0.06
    Act Density 0.001%

    No Known Activations