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

    Neuronpedia

    INDEX
    Explanations

    medical, scientific, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.75
    ol
    0.61
    et
    0.60
    is
    0.59
    en
    0.59
     on
    0.57
    one
    0.57
    a
    0.55
     v
    0.55
    b
    0.54
    POSITIVE LOGITS
     لیګ
    0.66
     آمریکا
    0.63
    ဂျ
    0.61
    ッジ
    0.61
    𝚇
    0.60
    メージ
    0.58
    ینګ
    0.57
    ்ட்
    0.56
    킷
    0.56
    ில்லியன்
    0.55
    Act Density 0.079%

    No Known Activations