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

    Neuronpedia

    INDEX
    Explanations

    the presence of structured document elements and content formats

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

    gender-based classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.50
    лтемелер
    -0.45
    comp
    -0.42
     OR
    -0.41
     Schmel
    -0.41
     rather
    -0.41
     Friedman
    -0.39
     and
    -0.39
    apo
    -0.38
     Aussch
    -0.38
    POSITIVE LOGITS
    endcsname
    0.52
    (!__
    0.52
    Autoritní
    0.52
     éditoriale
    0.51
     contextLoads
    0.50
     kasarigan
    0.50
    ✨:
    0.49
    GOTREF
    0.48
     propOrder
    0.47
    
    0.47
    Act Density 0.003%

    No Known Activations