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

    Neuronpedia

    INDEX
    Explanations

    periods, likely indicating sentence endings or punctuation in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by capitalization

    np_acts-logits-general · gemini-2.0-flash

    mixed language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.54
     precisione
    -0.49
    zeptember
    -0.48
     précision
    -0.47
     just
    -0.46
    SenderId
    -0.45
     recently
    -0.45
     Langkah
    -0.43
     over
    -0.43
    FTFY
    -0.43
    POSITIVE LOGITS
     الحره
    0.69
    はじめに
    0.66
    AnchorStyles
    0.66
    Datuak
    0.65
    feit
    0.65
    MLLoader
    0.64
    Geplaatst
    0.60
    ergies
    0.60
    abank
    0.60
     Penalty
    0.59
    Act Density 0.033%

    No Known Activations