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

    Neuronpedia

    INDEX
    Explanations

    truthful statements or assertions within the text

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

    Following "True" in math/logic contexts

    np_acts-logits-general · gemini-2.0-flash

    True statements or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IContainer
    -0.74
     AppBundle
    -0.59
    tagHelperRunner
    -0.57
     dysplasia
    -0.56
     armados
    -0.54
    HasForeignKey
    -0.53
    Démographie
    -0.52
    দ্
    -0.52
    yntaxException
    -0.51
     Rhymes
    -0.51
    POSITIVE LOGITS
    iramente
    0.77
     believers
    0.70
     believer
    0.70
     "")
    0.69
     AppComponent
    0.69
    uyler
    0.67
     colors
    0.65
     Grit
    0.63
     "");
    0.63
    öszi
    0.61
    Act Density 0.120%

    No Known Activations