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

    Neuronpedia

    INDEX
    Explanations

    terms related to vector space theory and mathematical structures

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

    Mathematical notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    articles defining mathematical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     progressively
    -0.43
    ⊗
    -0.40
     gradually
    -0.40
     virtual
    -0.40
     kira
    -0.38
     Tucker
    -0.38
     Q
    -0.38
    bruch
    -0.37
     phasing
    -0.37
     Lent
    -0.36
    POSITIVE LOGITS
     utafitiHapana
    0.60
    AnchorStyles
    0.59
     שוליים
    0.58
     تضيفلها
    0.57
    enderror
    0.57
     المعيارى
    0.57
    ValueStyle
    0.56
    RenderAtEndOf
    0.54
     Савезне
    0.54
     tartalomajánló
    0.53
    Act Density 1.322%

    No Known Activations