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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence and effects of variables in scientific contexts

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

    addition of number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.50
    contentLoaded
    -0.49
    ngdoc
    -0.48
    zzleHttp
    -0.48
    uxxxx
    -0.46
     fusca
    -0.42
    DeleteBehavior
    -0.40
     utafitiHapana
    -0.40
    MethodManager
    -0.38
    rospy
    -0.37
    POSITIVE LOGITS
    دانشنامهٔ
    0.56
    protoimpl
    0.43
     ویکی‌پدیای
    0.43
    참고
    0.41
     مشين
    0.40
     solvers
    0.38
     Diff
    0.37
    InputTagHelper
    0.37
    Diff
    0.37
    通
    0.36
    Act Density 0.537%

    No Known Activations