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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and vulnerabilities

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

    viruses, disease, health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.50
    UrlResolution
    -0.50
     typelib
    -0.50
    TagMode
    -0.45
    tableFuture
    -0.44
    Obrázky
    -0.44
    gione
    -0.40
    Хьажоргаш
    -0.40
    QUANTITY
    -0.40
    好好的
    -0.39
    POSITIVE LOGITS
    ſelf
    0.43
     Anſ
    0.43
    +#+#
    0.39
    Kariera
    0.38
     bluzka
    0.37
     Infórmanos
    0.36
    鲜血
    0.34
    舺
    0.33
    ิง
    0.33
    诊
    0.33
    Act Density 0.184%

    No Known Activations