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

    Neuronpedia

    INDEX
    Explanations

    ellipsis or pauses in dialogue indicative of hesitation or contemplation

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

    ITU Nurses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chargez
    -0.50
    <bos>
    -0.46
    -
    -0.42
    ガ
    -0.41
     gak
    -0.41
     Salom
    -0.40
    ValueGenerated
    -0.40
    надца
    -0.39
    filepath
    -0.37
     Botanic
    -0.37
    POSITIVE LOGITS
     ...
    0.70
     ......
    0.63
     ...'
    0.61
      
    0.61
     ..."
    0.60
     Crusoe
    0.60
    pense
    0.59
     ..........
    0.59
     .....
    0.59
     ....
    0.58
    Act Density 0.087%

    No Known Activations