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

    Neuronpedia

    INDEX
    Explanations

    elements of self-awareness and personal reflection

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

    after punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    fragile beginnings, efficacy, periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sl
    -0.35
    og
    -0.33
     rejection
    -0.33
     pal
    -0.32
     fell
    -0.31
    ----</
    -0.31
     Pad
    -0.30
    setSize
    -0.30
    ouv
    -0.30
    ensi
    -0.30
    POSITIVE LOGITS
    MessageTagHelper
    0.60
     صوتيه
    0.59
    yntaxException
    0.59
     myſelf
    0.57
     المعيارى
    0.56
     للاسماء
    0.54
    tanleria
    0.53
     queſta
    0.52
     
    0.52
     pinulongan
    0.52
    Act Density 1.063%

    No Known Activations