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

    Neuronpedia

    INDEX
    Explanations

    technical or programming terms and concepts related to coding and data structures

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

    interpreting structured information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.58
    hilangan
    -0.48
     Producción
    -0.47
     mendatang
    -0.44
     oprot
    -0.43
     soeur
    -0.43
     Wikiseite
    -0.42
     zanahoria
    -0.42
    twimg
    -0.41
    exitRule
    -0.41
    POSITIVE LOGITS
     mone
    0.44
     interpretations
    0.44
     interpretation
    0.44
     interpre
    0.42
     assimilation
    0.42
     Interpre
    0.41
     Interpretation
    0.41
     decoding
    0.40
    NINGS
    0.40
    ismet
    0.40
    Act Density 0.276%

    No Known Activations