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

    Neuronpedia

    INDEX
    Explanations

    statements expressing optimism or notable changes

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

    seriously good stuff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bahasan
    -0.35
    Safe
    -0.34
     maș
    -0.32
    lateinit
    -0.32
    τεύ
    -0.32
     împre
    -0.32
     Sav
    -0.31
    Vel
    -0.31
     المعيارى
    -0.31
    Phas
    -0.31
    POSITIVE LOGITS
     незавершена
    0.72
    səhifə
    0.57
    exitRule
    0.54
     consultato
    0.54
    RenderAtEndOf
    0.52
    utilisons
    0.51
     betweenstory
    0.50
    EndContext
    0.50
    تقاوى
    0.49
    indest
    0.47
    Act Density 0.098%

    No Known Activations