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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence endings

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

    Quotation marks followed by certain names

    np_acts-logits-general · gemini-2.0-flash

    end of quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.74
     "¡
    -0.71
    ChildScrollView
    -0.71
    GEBURTSDATUM
    -0.70
    UrlResolution
    -0.69
    ScopeManager
    -0.68
     "¿
    -0.67
     -->>
    -0.67
    AttributeSet
    -0.66
     NgModule
    -0.66
    POSITIVE LOGITS
    Indeed
    1.00
    Adds
    0.89
    Added
    0.85
     Indeed
    0.83
     Adds
    0.83
     indeed
    0.73
     added
    0.71
     lanjut
    0.68
    確かに
    0.68
     inderdaad
    0.67
    Act Density 0.070%

    No Known Activations