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

    Neuronpedia

    INDEX
    Explanations

    references to extremist ideologies and the psychological manipulation associated with them

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

    indoctrinated followers and fanatics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.57
    parsedMessage
    -0.50
    IBOutlet
    -0.47
    Географија
    -0.42
    Géographie
    -0.42
    kning
    -0.40
    viewBox
    -0.39
    FromNib
    -0.38
    gameObject
    -0.36
     يتيمه
    -0.36
    POSITIVE LOGITS
     SwitchCompat
    0.42
     Promised
    0.40
     followers
    0.40
     fanatic
    0.40
    momix
    0.40
     alfa
    0.40
     idr
    0.39
    extAlignment
    0.38
     Alpha
    0.37
    IsMutable
    0.37
    Act Density 0.064%

    No Known Activations