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

    Neuronpedia

    INDEX
    Explanations

    Bajrang, TF, diaz, pigment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    водит
    1.73
    𝘯
    1.67
    1.63
    вропей
    1.62
    1.62
    bericht
    1.62
    !\!\
    1.61
    tahun
    1.60
     번째
    1.59
     Utopia
    1.58
    POSITIVE LOGITS
    특별시
    1.73
    ri
    1.71
    rt
    1.61
    チック
    1.55
    EL
    1.54
    AT
    1.54
    ra
    1.53
    ro
    1.52
    ET
    1.50
    ten
    1.50
    Act Density 0.000%

    No Known Activations