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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated precision or variability

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

    values ± deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.41
     showcased
    -0.39
    findpost
    -0.39
    ekte
    -0.37
     lược
    -0.37
     siya
    -0.37
    わざわざ
    -0.36
     révélé
    -0.36
     demonstrated
    -0.36
     separated
    -0.35
    POSITIVE LOGITS
    addCriterion
    0.68
    AndEndTag
    0.60
     ComVisible
    0.57
    multer
    0.55
     <>",
    0.55
    GEBURTSDATUM
    0.52
    dafx
    0.52
     CascadeType
    0.51
     +/-
    0.50
     ब्रेकडाउन
    0.50
    Act Density 0.038%

    No Known Activations