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

    Neuronpedia

    INDEX
    Explanations

    direct speech or quotes in the text

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

    Follows commas or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted speech or inner thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.53
    ates
    -0.45
    []=$
    -0.44
    MON
    -0.43
    ()");
    -0.43
    mon
    -0.42
    hren
    -0.42
    ...");
    -0.42
     sord
    -0.41
     "/")
    -0.40
    POSITIVE LOGITS
     hey
    0.99
    tagHelperRunner
    0.97
     Hey
    0.89
    SharedCtor
    0.83
     HEY
    0.77
     fallu
    0.76
     oh
    0.76
    Hey
    0.76
    featureID
    0.75
     Here
    0.75
    Act Density 0.104%

    No Known Activations