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

    Neuronpedia

    INDEX
    Explanations

    symbols or formatting elements used in text, particularly asterisks and special character sequences

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

    bolded text segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.66
    <?
    -0.64
    AddTagHelper
    -0.61
    EndContext
    -0.57
     nakalista
    -0.55
    Hentet
    -0.54
     gynhyrchwyd
    -0.54
    CROSSTALK
    -0.51
    principalColumn
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
    Question
    0.47
     question
    0.47
     vertes
    0.45
     Question
    0.43
     Warning
    0.43
     quote
    0.42
    Warning
    0.42
     original
    0.40
     questions
    0.40
     warning
    0.40
    Act Density 0.018%

    No Known Activations