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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and constructs related to vector spaces and geometry

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

    Mathematical notation: superscripts and subscripts

    np_acts-logits-general · gemini-2.0-flash

    mathematical indices and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.42
     побу
    -0.40
     daly
    -0.38
    <i>
    -0.36
     Best
    -0.36
    MC
    -0.36
    olu
    -0.36
     مص
    -0.35
    存
    -0.35
     imper
    -0.35
    POSITIVE LOGITS
     تضيفلها
    0.99
    ]--;
    0.98
    StructEnd
    0.92
    AndEndTag
    0.91
    +#+
    0.90
     kaarangay
    0.89
     resourceCulture
    0.89
    :✨
    0.89
     fevere
    0.88
     tartalomajánló
    0.88
    Act Density 2.606%

    No Known Activations