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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations

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

    likely indices or counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.63
     الحره
    -0.63
    httphttps
    -0.60
    ſicht
    -0.55
     تضيفلها
    -0.54
    存于互联网档案馆
    -0.52
    最快更新
    -0.52
     nonUne
    -0.52
    }}]{
    -0.50
    <unused14>
    -0.49
    POSITIVE LOGITS
    rin
    0.35
     morire
    0.35
     chistes
    0.34
    farlane
    0.34
    enquête
    0.33
    1
    0.33
     anciennes
    0.32
     characters
    0.32
    EndContext
    0.31
     sœurs
    0.31
    Act Density 0.349%

    No Known Activations