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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jail
    -0.07
    agrams
    -0.06
    เหต
    -0.06
     Algebra
    -0.06
     algebra
    -0.06
    Media
    -0.06
    ẵng
    -0.06
     attributed
    -0.06
    agram
    -0.06
    awks
    -0.06
    POSITIVE LOGITS
    .onResume
    0.06
    ρωση
    0.06
    :this
    0.06
    %@",
    0.06
    ież
    0.06
    ως
    0.06
    .Pod
    0.06
    Unix
    0.06
     (){↵
    0.06
    favicon
    0.06
    Act Density 0.012%

    No Known Activations