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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or events in a community setting

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

    Formatting or punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whilst
    -1.02
    Whilst
    -0.94
    AndEndTag
    -0.88
     whilst
    -0.86
    luß
    -0.84
     anyways
    -0.82
     Amongst
    -0.81
    UrlResolution
    -0.77
     eighteen
    -0.77
    ियाँ
    -0.76
    POSITIVE LOGITS
     
    0.80
     —
    0.69
    ¦
    0.69
     
    0.62
    ,’’
    0.60
     היתה
    0.58
      
    0.58
     ‘‘
    0.54
     ¦
    0.54
     gerekiyor
    0.52
    Act Density 0.215%

    No Known Activations