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

    Neuronpedia

    INDEX
    Explanations

    inquiries about actions and their appropriateness or effectiveness

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

    future actions or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.59
    ParallelGroup
    -0.41
     Biôgrafia
    -0.41
    Билгалдахарш
    -0.40
    newswire
    -0.37
     okuyayım
    -0.36
     werd
    -0.36
    Vidite
    -0.35
    المشاركات
    -0.35
    Gweler
    -0.35
    POSITIVE LOGITS
    ftagPool
    0.52
    AndEndTag
    0.51
    Specyfikacja
    0.49
    DockStyle
    0.46
     setia
    0.43
     CreateTagHelper
    0.43
     simplicité
    0.43
    JsonInclude
    0.42
    Choice
    0.42
    izophren
    0.41
    Act Density 0.160%

    No Known Activations