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

    Neuronpedia

    INDEX
    Explanations

    words related to safety, security, and police presence

    oai_token-act-pair · gemini-2.0-flash

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.69
     Vitae
    -0.59
     betweenstory
    -0.56
    évaluateur
    -0.55
    WebElementEntity
    -0.54
     Process
    -0.53
     Vaters
    -0.53
     Vulkan
    -0.52
    usermodel
    -0.52
     envie
    -0.52
    POSITIVE LOGITS
     Segurança
    0.65
     security
    0.64
     segurança
    0.62
    ագրություններ
    0.61
     Security
    0.57
     assurent
    0.55
     Sicherheit
    0.55
     sécurité
    0.54
     Seguridad
    0.53
    setViewName
    0.52
    Act Density 1.793%

    No Known Activations