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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fifth
    -0.07
    _beh
    -0.07
     kø
    -0.07
    ㅋ
    -0.06
    ٍ
    -0.06
    (generator
    -0.06
    ého
    -0.06
    这么
    -0.06
    /ex
    -0.06
    งอย
    -0.06
    POSITIVE LOGITS
    Fade
    0.06
    .Requires
    0.06
     방
    0.06
    vang
    0.06
    IRROR
    0.06
     Dynam
    0.06
     Gratis
    0.06
    �
    0.06
    .Decode
    0.06
    舉
    0.06
    Act Density 0.041%

    No Known Activations