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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical specifications or data formats

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

    <start_of_turn>user turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.47
    fortawesome
    -0.40
    PROTOBUF
    -0.40
     Bogen
    -0.38
    lccn
    -0.38
    posób
    -0.34
     GenerationType
    -0.33
     Stamm
    -0.32
     Hochsch
    -0.32
     remplacé
    -0.32
    POSITIVE LOGITS
     EconPapers
    0.89
    期刊论文
    0.78
     iconLine
    0.73
     Numerade
    0.66
    出版年
    0.65
    .*")]
    0.61
    
    0.57
    contentLoaded
    0.56
     Photocase
    0.56
    TokenNameLBRACE
    0.54
    Act Density 0.026%

    No Known Activations