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

    Neuronpedia

    INDEX
    Explanations

    puted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hanno
    -0.07
    (type
    -0.07
    íně
    -0.07
    opleft
    -0.07
    otomy
    -0.07
     Lear
    -0.07
    وى
    -0.07
    (console
    -0.06
    scaling
    -0.06
    hhh
    -0.06
    POSITIVE LOGITS
     ジ
    0.08
    @FXML
    0.06
     omega
    0.06
     affiliate
    0.06
     Bey
    0.06
    ;(
    0.06
    cerr
    0.06
    guna
    0.06
    ่าส
    0.05
    -low
    0.05
    Act Density 0.002%

    No Known Activations