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

    Neuronpedia

    INDEX
    Explanations

    terms related to data filtering and sorting operations

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

    filter by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WEBPACK
    -0.42
     bedrag
    -0.40
    posedge
    -0.39
    wydd
    -0.39
    migrationBuilder
    -0.36
    Commands
    -0.36
     przys
    -0.35
    โย
    -0.35
    wieś
    -0.35
    newPassword
    -0.33
    POSITIVE LOGITS
     filter
    1.21
     Filter
    1.20
    Filter
    1.05
    filter
    1.02
     FILTER
    0.98
     filters
    0.94
     Filters
    0.94
     filtre
    0.89
    FILTER
    0.88
     filtro
    0.85
    Act Density 0.007%

    No Known Activations