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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and well-being advice

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

    conversational turns and user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >{@
    -0.38
     surla
    -0.37
     للمعارف
    -0.36
    tanleria
    -0.36
    Diweddarwch
    -0.36
    LayoutPanel
    -0.35
     iVar
    -0.34
    IContainer
    -0.34
     CGRect
    -0.33
     useCallback
    -0.32
    POSITIVE LOGITS
    NewUrlParser
    0.63
    reportWebVitals
    0.57
     kaarangay
    0.54
    izr
    0.52
    enumii
    0.52
    Rohy
    0.51
    Peace
    0.48
     AssemblyCompany
    0.48
    Portail
    0.47
     INTERESAR
    0.46
    Act Density 0.012%

    No Known Activations