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

    Neuronpedia

    INDEX
    Explanations

    acknowledgement and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextView
    0.42
     storyboard
    0.41
     Gmail
    0.40
    ovno
    0.40
    ́p
    0.38
     replacing
    0.38
     textural
    0.38
     replace
    0.38
     emailing
    0.38
    𝑂
    0.38
    POSITIVE LOGITS
     Emper
    0.40
     Hearing
    0.38
    Hearing
    0.38
     sinal
    0.37
     сигнал
    0.37
    GSM
    0.37
     रोल
    0.36
    放出
    0.36
     signalled
    0.36
    біль
    0.36
    Act Density 0.001%

    No Known Activations