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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting awareness or recognition of overlooked facts or truths

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

    preceding "is" or "that"

    np_acts-logits-general · gemini-2.0-flash

    information not realized or forgotten

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.57
    PerformLayout
    -0.55
    AddTagHelper
    -0.50
    JsonPropertyName
    -0.47
    enterOuterAlt
    -0.45
    rrggbb
    -0.43
     Taktlose
    -0.42
    makeConstraints
    -0.42
    icillin
    -0.42
     kasarigan
    -0.42
    POSITIVE LOGITS
     ignore
    0.39
    <bos>
    0.39
     Daß
    0.35
    GEBURTSDATUM
    0.35
     оригинала
    0.34
     untersch
    0.33
    PositiveButton
    0.33
    Ivory
    0.32
    ätigkeit
    0.32
    Ignore
    0.32
    Act Density 0.708%

    No Known Activations