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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, specifications, and characteristics of objects

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

    Comes before a unit of measure

    np_acts-logits-general · gemini-2.0-flash

    raw, unmodified, or measured states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.73
     '\\;'
    -0.66
    ()?;
    -0.63
     ISNI
    -0.57
    AutoresizingMask
    -0.56
    новништво
    -0.56
    reszcie
    -0.55
     jScrollPane
    -0.55
    Népesség
    -0.55
    tdessen
    -0.54
    POSITIVE LOGITS
     raw
    1.15
     un
    1.00
     naked
    0.96
     bare
    0.93
     uncut
    0.92
     unloaded
    0.92
     unmodified
    0.91
    raw
    0.90
     unpacked
    0.84
     untreated
    0.83
    Act Density 0.607%

    No Known Activations