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

    Neuronpedia

    INDEX
    Explanations

    national hotlines and institutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    0.94
    0
    0.88
     that
    0.82
    ation
    0.79
    ب
    0.79
    z
    0.78
    ur
    0.77
    s
    0.75
    <0x0D>
    0.72
    ina
    0.71
    POSITIVE LOGITS
    리
    0.90
    ла
    0.87
    )。
    0.84
    시
    0.84
    사
    0.81
    ুল
    0.79
    リ
    0.77
    으며
    0.74
    डी
    0.73
    )，
    0.73
    Act Density 0.147%

    No Known Activations