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

    Neuronpedia

    INDEX
    Explanations

    references to movies and their qualities

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

    conversational endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.67
    transQ
    -0.63
    endpush
    -0.62
    AutoField
    -0.62
    MigrationBuilder
    -0.60
    DoubleQuotes
    -0.59
     indígen
    -0.58
     Infórmanos
    -0.58
     propOrder
    -0.57
     HFILL
    -0.57
    POSITIVE LOGITS
     I
    0.47
     too
    0.46
     pretty
    0.44
     underrated
    0.44
     but
    0.43
     my
    0.40
     Mes
    0.39
     liked
    0.39
     Mar
    0.38
     My
    0.38
    Act Density 0.039%

    No Known Activations