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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الرئيس
    -0.07
     bundle
    -0.06
    τερη
    -0.06
    co
    -0.06
    戦
    -0.06
     Sonuç
    -0.06
    篇
    -0.06
    protobuf
    -0.06
     Adams
    -0.06
    America
    -0.06
    POSITIVE LOGITS
     Lyft
    0.07
    (ir
    0.07
     پایه
    0.07
    VAL
    0.07
    .validation
    0.06
    (elem
    0.06
     unaffected
    0.06
    رى
    0.06
     Bik
    0.06
    勤
    0.06
    Act Density 0.014%

    No Known Activations