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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents or crimes, specifically stabbings and murders

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

    murder occurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.52
     AttributeSet
    -0.45
     gehe
    -0.37
     nominees
    -0.37
    Nom
    -0.37
    RouterModule
    -0.36
    études
    -0.35
     Règlement
    -0.35
     industries
    -0.35
    regulatory
    -0.35
    POSITIVE LOGITS
    setVerticalGroup
    0.63
    verifyException
    0.60
     beginnetje
    0.57
    0.57
    GEBURTS
    0.55
    initComponents
    0.54
    kmale
    0.53
    featureID
    0.52
    principalColumn
    0.49
    UnitTesting
    0.48
    Act Density 0.063%

    No Known Activations