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

    Neuronpedia

    INDEX
    Explanations

    programming-related class and method definitions

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

    setting fields and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.83
    featureID
    -0.81
    rungsseite
    -0.79
    UserScript
    -0.79
    utilisons
    -0.77
     Roskov
    -0.77
     ब्रेकडाउन
    -0.77
    évaluateur
    -0.75
     يتيمه
    -0.74
    IUrlHelper
    -0.73
    POSITIVE LOGITS
    (
    0.60
     (
    0.51
     set
    0.40
    ()
    0.37
     changed
    0.34
    set
    0.34
    (@
    0.33
    Changed
    0.33
     to
    0.32
     vē
    0.32
    Act Density 0.007%

    No Known Activations