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

    Neuronpedia

    INDEX
    Explanations

    any amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப
    0.49
    0.47
    The
    0.47
     scars
    0.42
         
    0.41
    你
    0.39
    You
    0.38
    В
    0.38
     unit
    0.37
    Featured
    0.37
    POSITIVE LOGITS
    cevam
    0.53
     форму
    0.48
     Ergebn
    0.48
    सीय
    0.47
     magni
    0.46
    SizeF
    0.46
     челу
    0.46
     Cura
    0.46
    nY
    0.45
     Jehovah
    0.45
    Act Density 0.000%

    No Known Activations