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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пла
    -0.06
    BL
    -0.06
     sufferers
    -0.06
     바이
    -0.06
     برگز
    -0.06
     Ja
    -0.06
    마사지
    -0.06
     Established
    -0.06
    kyně
    -0.06
    達
    -0.06
    POSITIVE LOGITS
    'ex
    0.07
    .Num
    0.07
     अ
    0.07
    perm
    0.07
    _SELF
    0.07
    DOM
    0.06
    ंक
    0.06
    /↵↵↵↵
    0.06
    ause
    0.06
     itertools
    0.06
    Act Density 0.063%

    No Known Activations