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

    Neuronpedia

    INDEX
    Explanations

    negative or dismissive references to people or things in a contextually frustrating or trivial manner

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

    nothing, nowhere, nobody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.47
    WebpackPlugin
    -0.37
    botella
    -0.37
     forstå
    -0.36
    Izvori
    -0.36
     Wake
    -0.35
    warnai
    -0.35
     mức
    -0.34
    Pyx
    -0.33
     Verständnis
    -0.33
    POSITIVE LOGITS
     nowhere
    0.91
    nothing
    0.90
     nothing
    0.90
    Nothing
    0.86
     Nothing
    0.84
    Nowhere
    0.82
     Nowhere
    0.80
    NOTHING
    0.76
     NOTHING
    0.75
     nada
    0.74
    Act Density 0.029%

    No Known Activations