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

    Neuronpedia

    INDEX
    Explanations

    terms related to acknowledgment or recognition

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

    acknowledges, reserves, opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.51
     تضيفلها
    -0.49
    MessageTagHelper
    -0.47
     nakalista
    -0.46
    Personensuche
    -0.43
     gills
    -0.43
    yled
    -0.42
     purer
    -0.42
    InitVars
    -0.42
    ibase
    -0.41
    POSITIVE LOGITS
     itself
    0.63
    SourceChecksum
    0.47
    XmlRootElement
    0.45
    itself
    0.44
     zostało
    0.42
    BASEPATH
    0.41
     Itself
    0.40
     aussieht
    0.40
    といけない
    0.40
     its
    0.39
    Act Density 0.050%

    No Known Activations