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

    Neuronpedia

    INDEX
    Explanations

    Friends TV show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‌است
    0.95
     interchangeably
    0.90
    ي
    0.89
    y
    0.89
    b
    0.89
    p
    0.86
    and
    0.85
     obsess
    0.85
     Postgres
    0.85
     CONCLUS
    0.85
    POSITIVE LOGITS
    ડ
    0.89
    treatment
    0.84
    tid
    0.83
    摔
    0.80
    ます
    0.77
    ј
    0.77
    <0xA6>
    0.77
    год
    0.77
    tone
    0.76
    有过
    0.75
    Act Density 0.003%

    No Known Activations