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

    Neuronpedia

    INDEX
    Explanations

    Asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     işlemi
    -0.07
    ABB
    -0.06
     ا�
    -0.06
     labour
    -0.06
    omal
    -0.06
     WPARAM
    -0.06
     didnt
    -0.06
    .gray
    -0.06
     ориг
    -0.06
    antis
    -0.06
    POSITIVE LOGITS
    course
    0.07
    !
↵
    0.06
    。”↵↵
    0.06
    {T
    0.06
     doprav
    0.06
     ↵
    0.06
    _uv
    0.06
     Greatest
    0.06
     ingestion
    0.06
    cház
    0.06
    Act Density 0.001%

    No Known Activations