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

    Neuronpedia

    INDEX
    Explanations

    kirk followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blum
    0.40
    ’
    0.40
     start
    0.40
     Rather
    0.38
    br
    0.38
    asam
    0.37
     выступи
    0.37
     Pember
    0.37
    llo
    0.37
    reli
    0.36
    POSITIVE LOGITS
     رکھنے
    0.40
    empê
    0.40
     KIR
    0.40
    ܠܐ
    0.39
    খাল
    0.38
    michael
    0.38
     diffé
    0.37
    下图
    0.37
     നൂ
    0.37
     çöz
    0.37
    Act Density 0.000%

    No Known Activations