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

    Neuronpedia

    INDEX
    Explanations

    Here', 'your', 'Universities', 'browser'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    1.09
    TC
    1.00
     T
    0.97
    Ｔ
    0.97
    Т
    0.91
    Tin
    0.86
     t
    0.85
     tin
    0.84
     Tin
    0.83
    TI
    0.82
    POSITIVE LOGITS
    م
    0.66
    m
    0.64
    marshaller
    0.63
    ɱ
    0.63
     সু
    0.62
    𝗺
    0.60
    میری
    0.59
     Mothers
    0.58
     Lim
    0.58
    mas
    0.58
    Act Density 0.242%

    No Known Activations