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

    Neuronpedia

    INDEX
    Explanations

    expressions of discontent or displeasure

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

    making things clear or expressed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.48
     éc
    -0.44
     Auft
    -0.44
    LabelTagHelper
    -0.44
    DoubleQuotes
    -0.43
    éndole
    -0.42
    powering
    -0.41
    unjang
    -0.41
    clusão
    -0.40
     HttpNotFound
    -0.40
    POSITIVE LOGITS
     expresses
    0.56
    Express
    0.53
     express
    0.52
     Express
    0.50
     expressing
    0.49
    表達
    0.48
    表明
    0.48
     EXPRESS
    0.47
    表达
    0.47
     manifesta
    0.46
    Act Density 0.215%

    No Known Activations