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

    Neuronpedia

    INDEX
    Explanations

    step-by-step guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ection
    0.72
     platter
    0.71
    ত্ত
    0.70
     slant
    0.70
    ixed
    0.70
     пас
    0.70
    aster
    0.70
    शाली
    0.69
    ಟ್
    0.69
    jmp
    0.69
    POSITIVE LOGITS
    丁寧に
    1.02
    PING
    0.87
    anjay
    0.86
    hen
    0.85
     taken
    0.84
    hens
    0.84
     জনগোষ্ঠ
    0.82
    listItem
    0.81
    上有
    0.80
    丁寧
    0.79
    Act Density 0.112%

    No Known Activations