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

    Neuronpedia

    INDEX
    Explanations

    expressions related to fear and warnings

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

    exclamations and common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.73
     AssemblyCulture
    -0.71
    \{\\
    -0.69
    AndEndTag
    -0.66
    -0.66
    WindowConstants
    -0.65
    gonic
    -0.65
    IContainer
    -0.64
    MethodManager
    -0.63
     poffible
    -0.62
    POSITIVE LOGITS
     indeed
    0.39
    녕
    0.37
     nonetheless
    0.37
    awakeFromNib
    0.36
     albeit
    0.35
     سام
    0.35
     arises
    0.34
    ken
    0.34
     Hallen
    0.33
    .
    0.33
    Act Density 0.065%

    No Known Activations