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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    芽
    0.64
    ほぼ
    0.63
     incest
    0.62
     Molding
    0.62
    撹
    0.61
     엄청
    0.61
     पूर्वक
    0.60
    様々な
    0.59
    ッケ
    0.58
    籾
    0.57
    POSITIVE LOGITS
    guan
    0.58
     เอก
    0.57
     dian
    0.56
     teman
    0.55
    ^{(
    0.54
     clicked
    0.54
     subscribed
    0.53
     mengenal
    0.53
     coche
    0.53
     Guan
    0.53
    Act Density 0.000%

    No Known Activations