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

    Neuronpedia

    INDEX
    Explanations

    concepts related to vulnerability and susceptibility in various contexts

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

    vulnerable or susceptible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.59
     kasarigan
    -0.56
    FetchType
    -0.45
     uLocal
    -0.44
    MessageTagHelper
    -0.44
    RegressionTest
    -0.44
     FormData
    -0.43
    (!__
    -0.43
     PeEnEo
    -0.42
    nein
    -0.41
    POSITIVE LOGITS
     vulnerable
    1.94
     vulnerability
    1.85
     susceptible
    1.71
     susceptibility
    1.68
     Vulnerable
    1.66
     vulné
    1.57
     vulnerables
    1.52
     Vulnerability
    1.49
     vulner
    1.48
    vul
    1.46
    Act Density 0.204%

    No Known Activations