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

    Neuronpedia

    INDEX
    Explanations

    punctuation, who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     postponed
    -0.06
     stesso
    -0.06
    строй
    -0.06
     kiş
    -0.06
     Container
    -0.06
    anders
    -0.05
     compartments
    -0.05
    _unix
    -0.05
    410
    -0.05
    imbus
    -0.05
    POSITIVE LOGITS
     GAME
    0.07
    (emp
    0.07
    ременно
    0.06
    "in
    0.06
    _DIR
    0.06
    :test
    0.06
    _SOFT
    0.06
    (u
    0.06
    scores
    0.06
    sap
    0.06
    Act Density 0.120%

    No Known Activations