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

    Neuronpedia

    INDEX
    Explanations

    structured lists containing bullet points or numbered items

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

    Tokens preceding bullet points or dashes

    np_acts-logits-general · gemini-2.0-flash

    documentation, gender, or technical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.57
     müſſen
    -0.55
     Italijani
    -0.54
    rrggbb
    -0.53
    richTextPanel
    -0.53
    ViewFeatures
    -0.52
    AddTagHelper
    -0.52
    Хьажоргаш
    -0.52
    aarrggbb
    -0.51
    InInspector
    -0.50
    POSITIVE LOGITS
    The
    0.60
     The
    0.57
     We
    0.44
    __(/*!
    0.43
    In
    0.43
    No
    0.42
    There
    0.42
    Also
    0.42
    For
    0.42
    If
    0.41
    Act Density 0.191%

    No Known Activations