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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases indicating actions and reactions related to violence and questioning

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

    specific names or place identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.44
     Cage
    -0.34
     FetchType
    -0.33
     iconLine
    -0.32
     getRule
    -0.31
     Audiodateien
    -0.31
     litt
    -0.30
    Cage
    -0.29
     cort
    -0.29
     Worm
    -0.28
    POSITIVE LOGITS
    ########.
    0.67
     فريبيس
    0.66
     Roskov
    0.61
    Diwedd
    0.55
    NameInMap
    0.54
    الإنجليزية
    0.53
     camiset
    0.53
    Havolalar
    0.52
    oluene
    0.52
     Administrativna
    0.52
    Act Density 0.086%

    No Known Activations