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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash

    exclamation marks signaling enthusiastic or polite openings in assistant responses.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ngine
    -0.08
    _axes
    -0.07
    BindView
    -0.07
    _sqrt
    -0.07
    .ResumeLayout
    -0.07
    _mu
    -0.07
    Disconnect
    -0.06
    Debug
    -0.06
     responded
    -0.06
    ESSAGE
    -0.06
    POSITIVE LOGITS
    比例
    0.07
     depletion
    0.07
     Klo
    0.07
    获得更多
    0.07
    employment
    0.07
     purely
    0.07
     ושל
    0.07
    类似的
    0.06
    创造
    0.06
    .Companion
    0.06
    Act Density 0.029%

    No Known Activations