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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech or quotations

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

    The apostrophe token

    np_acts-logits-general · gemini-2.0-flash

    URL, punctuation, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षाओं
    -0.78
    nologue
    -0.69
    balleur
    -0.66
    ANDUM
    -0.66
    findpost
    -0.65
     GenerationType
    -0.65
    hoeddwyd
    -0.65
     ostavi
    -0.62
    AlterField
    -0.61
    oa̍t
    -0.60
    POSITIVE LOGITS
    http
    0.78
    https
    0.64
    I
    0.64
     <<<<<<<<<<<<<<
    0.59
    …
    0.59
    ….
    0.58
     http
    0.56
    …”
    0.54
    Source
    0.54
    ....
    0.53
    Act Density 0.185%

    No Known Activations