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

    Neuronpedia

    INDEX
    Explanations

    incidents related to violence or fatalities

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

    events or occurrences

    np_acts-logits-general · gemini-2.0-flash

    accidents and occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    -0.54
    NameInMap
    -0.51
    เฉพาะ
    -0.50
    ztyn
    -0.47
     forever
    -0.47
     key
    -0.47
    rimid
    -0.46
     even
    -0.45
     every
    -0.45
    delà
    -0.44
    POSITIVE LOGITS
     reportedly
    0.84
     فريبيس
    0.82
     allegedly
    0.76
     diduga
    0.73
    apparently
    0.73
     madrugada
    0.72
    near
    0.72
     approximately
    0.71
    approximately
    0.71
     Seorang
    0.70
    Act Density 0.201%

    No Known Activations