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

    Neuronpedia

    INDEX
    Explanations

    compare strings or chemical reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toro
    0.52
     splitpos
    0.50
    0.48
    粞
    0.48
    λού
    0.47
     chub
    0.47
     สู
    0.47
    jadi
    0.47
    ImageQueue
    0.47
    at
    0.46
    POSITIVE LOGITS
     explore
    0.47
     explain
    0.45
     diantaranya
    0.43
     explains
    0.43
     என்
    0.42
     effic
    0.41
    écut
    0.40
     essential
    0.40
    মোঃ
    0.40
     İşte
    0.40
    Act Density 0.000%

    No Known Activations