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

    Neuronpedia

    INDEX
    Explanations

    passages of text that are argumentative and/or critical

    oai_token-act-pair · gemini-2.0-flash

    say "-ly" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.77
    migrationBuilder
    -0.69
    Biographie
    -0.69
     виправивши
    -0.65
     estekak
    -0.65
    expandindo
    -0.59
    Sucesor
    -0.57
    ільки
    -0.54
    tvguidetime
    -0.54
    iencies
    -0.52
    POSITIVE LOGITS
     musically
    1.13
     financially
    1.09
     visually
    0.98
     academically
    0.94
     culturally
    0.94
     economically
    0.93
     optically
    0.90
     technically
    0.89
     geographically
    0.88
     structurally
    0.87
    Act Density 9.734%

    No Known Activations