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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �y
    -0.08
    ullen
    -0.07
    Never
    -0.06
    ceu
    -0.06
     bana
    -0.06
    .Generic
    -0.06
     brutality
    -0.06
    +w
    -0.06
     neredeyse
    -0.06
    дап
    -0.06
    POSITIVE LOGITS
    대행
    0.06
    城
    0.06
    _filters
    0.06
    ********************************************************
    0.06
     authentication
    0.06
    .carousel
    0.06
    -name
    0.06
    ╗
    0.06
    transforms
    0.06
    ुह
    0.06
    Act Density 0.060%

    No Known Activations