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

    Neuronpedia

    INDEX
    Explanations

    elements related to physical properties and performance metrics in engineering contexts

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

    increase orimprove things; avoid negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.35
     PublicKey
    -0.34
     verdi
    -0.33
    isDebugEnabled
    -0.33
    RegressionTest
    -0.32
     BoxDecoration
    -0.31
    Jeografia
    -0.31
    TestBed
    -0.30
    richText
    -0.30
     mergeFrom
    -0.30
    POSITIVE LOGITS
    0.61
     ujednoznacz
    0.61
     Wikimedijinoj
    0.59
    IntoConstraints
    0.57
    TagMode
    0.55
     للمعارف
    0.53
    存于互联网档案馆
    0.51
     configuración
    0.50
    IndentedString
    0.48
    åter
    0.48
    Act Density 0.079%

    No Known Activations