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

    Neuronpedia

    INDEX
    Explanations

    Social issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
    Higher
    -0.07
     NPCs
    -0.07
    /**<
    -0.07
     scholarships
    -0.06
     чт
    -0.06
    structors
    -0.06
     Lancaster
    -0.06
    作者所有
    -0.06
    הוצאה
    -0.06
    POSITIVE LOGITS
     @$
    0.07
    _demo
    0.07
    暴风
    0.07
     인정
    0.07
     syscall
    0.07
    系列
    0.07
    舰队
    0.07
    .rule
    0.07
    嫣
    0.07
     valide
    0.07
    Act Density 0.237%

    No Known Activations