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

    Neuronpedia

    INDEX
    Explanations

    character sequences and special formatting tags

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

    Text within quotation marks, followed by "when"

    np_acts-logits-general · gemini-2.0-flash

    quoted conditional phrases concerning "when" or "who"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.74
    UnusedPrivate
    -0.68
    AddTagHelper
    -0.67
    enumii
    -0.67
     utafitiHapana
    -0.61
    Datuak
    -0.59
    Примітки
    -0.54
    adpleegd
    -0.52
    öße
    -0.52
    Nevermind
    -0.52
    POSITIVE LOGITS
    orks
    0.65
    orld
    0.60
    hich
    0.59
    ork
    0.58
    orking
    0.57
    hile
    0.57
    hite
    0.56
    ORK
    0.55
    akyti
    0.50
     gunner
    0.49
    Act Density 0.138%

    No Known Activations