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

    Neuronpedia

    INDEX
    Explanations

    in, inside, on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    2.05
    n
    1.84
    ar
    1.79
    ul
    1.60
    d
    1.58
    r
    1.51
    c
    1.48
    র
    1.46
    t
    1.44
    в
    1.41
    POSITIVE LOGITS
    टेन
    1.77
    の一
    1.63
    हदी
    1.58
    ꯋ
    1.57
    ματος
    1.55
    ાઓ
    1.51
    ]!=
    1.50
    外的
    1.48
    提到的
    1.48
     जाऊन
    1.47
    Act Density 0.033%

    No Known Activations