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

    Neuronpedia

    INDEX
    Explanations

    questions regarding authorship and accountability in creative works

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

    Lyrics or poems

    np_acts-logits-general · gemini-2.0-flash

    trust and faith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -1.06
    verwijspagina
    -0.96
    цездатний
    -0.96
     disambiguazione
    -0.96
    RenderAtEndOf
    -0.93
    InjectAttribute
    -0.92
     raiſ
    -0.91
     <<<<<<<<<<<<<<
    -0.90
     Autorizaciones
    -0.90
    writeField
    -0.90
    POSITIVE LOGITS
    full
    0.46
    '
    0.41
     full
    0.40
     assay
    0.40
    laway
    0.39
     upon
    0.39
    就不
    0.39
     o
    0.39
    vora
    0.38
     And
    0.38
    Act Density 0.099%

    No Known Activations