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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kens
    -0.08
    _RUN
    -0.07
    Cou
    -0.07
    .add
    -0.07
    .sin
    -0.06
    (TEST
    -0.06
    好
    -0.06
    interop
    -0.06
    scope
    -0.06
    acebook
    -0.06
    POSITIVE LOGITS
     anon
    0.07
    _under
    0.07
     國
    0.06
    MetaData
    0.06
     beaches
    0.06
     При
    0.06
    enin
    0.06
     undermin
    0.06
    iação
    0.06
     клі
    0.06
    Act Density 0.014%

    No Known Activations