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

    Neuronpedia

    INDEX
    Explanations

    potential market, already furiously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     No
    0.51
     Um
    0.50
    by
    0.49
    hs
    0.47
     MB
    0.47
    汲
    0.47
     For
    0.46
     Web
    0.45
     Ok
    0.45
     browsing
    0.44
    POSITIVE LOGITS
     Antwort
    0.45
     तलाक
    0.45
    ίναι
    0.42
    ἁ
    0.42
    валася
    0.42
     Finanz
    0.42
    зиру
    0.42
    грама
    0.41
    rocities
    0.41
     আর্ম
    0.41
    Act Density 0.001%

    No Known Activations