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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Visitors
    -0.08
     Ronald
    -0.08
    stor
    -0.07
    ポイ
    -0.07
    bulan
    -0.07
     monumental
    -0.07
     Woj
    -0.06
     queue
    -0.06
    pto
    -0.06
    ranges
    -0.06
    POSITIVE LOGITS
     진
    0.08
     Doesn
    0.08
    આ
    0.07
    .sim
    0.07
    HAS
    0.07
     specifics
    0.07
    瓒
    0.06
    ILogger
    0.06
    ⾊
    0.06
    аниз
    0.06
    Act Density 0.025%

    No Known Activations