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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ند
    -0.07
     glean
    -0.06
     influ
    -0.06
    GEST
    -0.06
    штов
    -0.06
    atan
    -0.06
     bond
    -0.06
    ."]↵
    -0.06
    .Res
    -0.06
    .Left
    -0.06
    POSITIVE LOGITS
    3
    0.09
    5
    0.09
    4
    0.08
    copy
    0.07
     sudah
    0.07
    間に
    0.07
     sitesi
    0.06
    kv
    0.06
     第三
    0.06
    धर
    0.06
    Act Density 0.038%

    No Known Activations