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

    Neuronpedia

    INDEX
    Explanations

    High quality/Advanced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     both
    -0.07
     FACT
    -0.06
    summary
    -0.06
     Apart
    -0.06
     Having
    -0.06
     ventilation
    -0.06
    .Out
    -0.06
    、マ
    -0.06
     Examples
    -0.06
    _MC
    -0.06
    POSITIVE LOGITS
     cherish
    0.06
    _ER
    0.06
    ：「
    0.06
    Soon
    0.06
     Soon
    0.06
    /flutter
    0.06
    mun
    0.06
    xiety
    0.06
     میلادی
    0.06
     LOGIN
    0.06
    Act Density 0.112%

    No Known Activations