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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and variables in a specific context

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

    Mathematical or linear algebra terms

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation like dimension or trace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.68
    DockStyle
    -0.57
    -0.57
     invokingState
    -0.56
    autoreleasepool
    -0.54
    idados
    -0.53
     تكبرها
    -0.52
     Мексичка
    -0.52
    مزید
    -0.49
    OpenHelper
    -0.48
    POSITIVE LOGITS
     rank
    0.71
    rank
    0.68
     dim
    0.64
     supp
    0.61
     Trace
    0.61
     trace
    0.60
    operatorname
    0.60
    lim
    0.60
    tr
    0.60
    limin
    0.60
    Act Density 2.707%

    No Known Activations