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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Berry
    -0.07
     katı
    -0.06
    ck
    -0.06
    -job
    -0.06
    /(
    -0.06
    闭
    -0.06
    _bbox
    -0.06
    timestamp
    -0.06
     automate
    -0.06
    Echo
    -0.05
    POSITIVE LOGITS
    reg
    0.07
     inn
    0.06
    ธน
    0.06
     Diğer
    0.06
     Roosevelt
    0.06
     Про
    0.06
     Ning
    0.06
    didn
    0.06
     type
    0.06
     consideration
    0.06
    Act Density 0.021%

    No Known Activations