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

    Neuronpedia

    INDEX
    Explanations

    scams/phishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vé
    -0.07
    (prom
    -0.07
     Constantin
    -0.07
     Gir
    -0.07
     Essence
    -0.06
    詩
    -0.06
    腐败
    -0.06
    🅛
    -0.06
    одерж
    -0.06
     fairness
    -0.06
    POSITIVE LOGITS
    -------↵↵
    0.08
    笔者
    0.07
    ClickListener
    0.07
    候选人
    0.07
     setHidden
    0.07
    (Main
    0.07
    ------↵↵
    0.07
    intros
    0.07
    ลบ
    0.07
    先天
    0.07
    Act Density 0.035%

    No Known Activations