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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eller
    0.26
     whiche
    0.25
     тощо
    0.25
     underside
    0.25
     എന്നിവ
    0.25
     honom
    0.24
     videre
    0.24
     nebo
    0.24
     मदत
    0.24
     möglicherweise
    0.24
    POSITIVE LOGITS
    best
    0.27
    ba
    0.27
     가장
    0.27
     अच्छी
    0.26
     наиболее
    0.26
    いち
    0.26
    eer
    0.26
    ley
    0.26
    das
    0.26
    bh
    0.25
    Act Density 0.011%

    No Known Activations