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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and threats

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

    attacks or invaders

    np_acts-logits-general · gemini-2.0-flash

    hostile actions and actors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.50
     للاسماء
    -0.47
     wikipagina
    -0.46
     Signalez
    -0.45
    LLocation
    -0.45
    GOTREF
    -0.44
     vixion
    -0.44
     Connectez
    -0.43
    SourceChecksum
    -0.42
     embarazada
    -0.42
    POSITIVE LOGITS
     threats
    0.54
    CodedInputStream
    0.50
     attackers
    0.49
     attack
    0.48
     thieves
    0.48
     predators
    0.47
     attacks
    0.47
     assailants
    0.46
     ladr
    0.45
     hackers
    0.44
    Act Density 0.362%

    No Known Activations