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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data handling and processing operations

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

    Text inside square brackets

    np_acts-logits-general · gemini-2.0-flash

    reference to specific data or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ecutive
    -0.98
    hematical
    -0.96
    ratulations
    -0.89
    ercises
    -0.89
    polation
    -0.85
    intenance
    -0.85
    Temperatura
    -0.85
    elfare
    -0.82
    aquarium
    -0.82
    haustible
    -0.82
    POSITIVE LOGITS
    se
    0.82
    var
    0.80
    _
    0.77
    sp
    0.75
    esti
    0.74
    v
    0.73
    x
    0.72
    f
    0.72
    by
    0.72
    b
    0.71
    Act Density 0.611%

    No Known Activations