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

    Neuronpedia

    INDEX
    Explanations

    code and regex snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сли
    -0.07
    .isFile
    -0.07
     analsex
    -0.06
     Waterproof
    -0.06
     waterproof
    -0.06
    144
    -0.06
    .cpu
    -0.06
     sacrificed
    -0.06
    _file
    -0.06
     orbital
    -0.06
    POSITIVE LOGITS
    >↵
    0.08
     successors
    0.07
    sav
    0.07
     Başkan
    0.07
    .Serialization
    0.06
     concerning
    0.06
    (geometry
    0.06
    ILON
    0.06
    东
    0.06
    >
↵
    0.06
    Act Density 0.000%

    No Known Activations