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

    Neuronpedia

    INDEX
    Explanations

    book spines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İN
    1.10
     Minggu
    1.01
    r
    0.99
    utente
    0.98
    zł
    0.96
    ması
    0.96
    ઓ
    0.95
     pesante
    0.95
    İL
    0.95
    ol
    0.93
    POSITIVE LOGITS
     Abuse
    1.13
    gruppe
    0.98
    ное
    0.90
    ेड
    0.90
    ্ড
    0.88
     составе
    0.87
    含量
    0.86
     воздей
    0.85
     PX
    0.83
     вопро
    0.83
    Act Density 0.000%

    No Known Activations