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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their context within time-related phrases

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

    quantities and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oublier
    -0.31
     verdade
    -0.30
     esterni
    -0.30
    Pvt
    -0.29
     Erziehung
    -0.29
     forget
    -0.28
    أة
    -0.28
     înal
    -0.27
     забы
    -0.27
    lık
    -0.27
    POSITIVE LOGITS
    astify
    0.69
    AnchorStyles
    0.67
     <<<<<<<<<<<<<<
    0.65
    WebVitals
    0.62
     تضيفلها
    0.62
     fashiola
    0.62
    maining
    0.62
    tangentMode
    0.61
     modelAndView
    0.60
    WithMany
    0.58
    Act Density 0.018%

    No Known Activations