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

    Neuronpedia

    INDEX
    Explanations

    you like or care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kann
    0.52
     फायदे
    0.50
    的朋友
    0.50
     tiem
    0.50
     μπορεί
    0.49
     Sistema
    0.49
    曰
    0.48
    琭
    0.47
     Isi
    0.47
    やかな
    0.47
    POSITIVE LOGITS
     despatched
    1.02
     discover
    0.90
     eradicate
    0.88
     discovered
    0.86
     acquire
    0.85
     utilized
    0.85
     obtainable
    0.84
     scrumptious
    0.84
     obtain
    0.84
     discovering
    0.84
    Act Density 0.003%

    No Known Activations