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

    Neuronpedia

    INDEX
    Explanations

    form submit button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    柽
    0.28
    TiO
    0.27
    ریر
    0.26
    ന്തപു
    0.25
    PAAm
    0.25
     titik
    0.25
    точ
    0.25
    TIL
    0.25
    یرہ
    0.24
    द्रा
    0.24
    POSITIVE LOGITS
    c
    0.29
    na
    0.26
     i
    0.25
    r
    0.25
    j
    0.25
    w
    0.24
    l
    0.24
    nn
    0.23
    ',
    0.23
    ll
    0.23
    Act Density 0.021%

    No Known Activations