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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insomnia
    -0.08
    볼
    -0.08
    mó
    -0.07
    lí
    -0.07
    ple
    -0.07
    olidays
    -0.07
    oho
    -0.07
    ónica
    -0.06
    ITTLE
    -0.06
    fon
    -0.06
    POSITIVE LOGITS
     rate
    0.11
     rates
    0.10
    _rate
    0.08
     Rate
    0.08
    rated
    0.08
    𝓽
    0.07
     Wyatt
    0.07
     מחיר
    0.07
    流传
    0.07
     regardless
    0.07
    Act Density 0.047%

    No Known Activations