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

    Neuronpedia

    INDEX
    Explanations

    components related to authorship and contributions in research documents

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

    indicates significant changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordinaires
    -0.61
     honnête
    -0.48
     canali
    -0.48
     ruines
    -0.48
     sauvages
    -0.47
    ResponseWriter
    -0.45
     variés
    -0.45
    arsky
    -0.44
     réserver
    -0.43
     gelegen
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.80
    enterOuterAlt
    0.76
    تقاوى
    0.75
     MainAxisSize
    0.75
    LabelTagHelper
    0.74
     صوتيه
    0.73
    InjectAttribute
    0.71
     Signalez
    0.71
    Indicates
    0.70
     متعلقه
    0.69
    Act Density 0.238%

    No Known Activations