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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents and criminal charges related to murder and assault

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

    preceding circumstances or causes

    np_acts-logits-general · gemini-2.0-flash

    accidents during events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Demografía
    -0.66
    دانشنامهٔ
    -0.60
     always
    -0.57
    hichever
    -0.57
    السكان
    -0.56
    AxisAlignment
    -0.56
     Administrativna
    -0.55
    Wherever
    -0.54
     längst
    -0.53
    always
    -0.51
    POSITIVE LOGITS
     allegedly
    0.80
     Seorang
    0.77
     accidentally
    0.73
     reportedly
    0.72
     فريبيس
    0.71
     during
    0.70
     near
    0.69
     causing
    0.68
     caused
    0.68
     diduga
    0.68
    Act Density 0.447%

    No Known Activations