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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating help or support related to assistance and guidance

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

    guidance and assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.48
     contextLoads
    -0.38
     Grüsse
    -0.38
    protetor
    -0.38
    antikan
    -0.38
    Приятного
    -0.38
     dataSnapshot
    -0.38
     calcetines
    -0.37
     Herausforderung
    -0.35
     Geiſt
    -0.35
    POSITIVE LOGITS
    CloseOperation
    0.63
     snippetHide
    0.58
     Assisted
    0.55
    fillType
    0.54
    oneofs
    0.48
    HasAnnotation
    0.48
     Supported
    0.47
     assisted
    0.47
    NewUrlParser
    0.46
    
    0.46
    Act Density 0.133%

    No Known Activations