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

    Neuronpedia

    INDEX
    Explanations

    no significant content, as all activation values are zero

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

    Follows "Q:" or hyphen

    np_acts-logits-general · gemini-2.0-flash

    question markers like Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.67
    Архівовано
    -0.55
    istoitu
    -0.53
     оригіналу
    -0.53
    |}{$
    -0.51
    bootstrapcdn
    -0.49
    PhysRevLett
    -0.48
    ſhip
    -0.48
     referrerpolicy
    -0.47
    ěstí
    -0.47
    POSITIVE LOGITS
    ьаж
    0.85
    AddTagHelper
    0.66
    rój
    0.64
     kasarigan
    0.56
    contentLoaded
    0.55
    ↵↵
    0.55
    RectangleBorder
    0.55
    SourceChecksum
    0.54
    ArgsConstructor
    0.54
    0.54
    Act Density 0.100%

    No Known Activations