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

    Neuronpedia

    INDEX
    Explanations

    amplified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OA
    -0.08
    .).
    -0.08
    蓐
    -0.07
    student
    -0.07
    ].'
    -0.06
    _SMS
    -0.06
    �
    -0.06
    扫一
    -0.06
     יצא
    -0.06
    EmptyEntries
    -0.06
    POSITIVE LOGITS
     Jake
    0.08
    𝘬
    0.07
    iktig
    0.06
    bourg
    0.06
    Messages
    0.06
     gibi
    0.06
     vời
    0.06
    gi
    0.06
     Carolyn
    0.06
    isms
    0.06
    Act Density 0.078%

    No Known Activations