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

    Neuronpedia

    INDEX
    Explanations

    discussions of product details and specifications

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

    descriptions and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.79
     تضيفلها
    -0.72
    tinyos
    -0.61
     ब्रेकडाउन
    -0.60
     Exactos
    -0.60
     незавершена
    -0.58
     snippetHide
    -0.58
    IsContent
    -0.57
    abetes
    -0.56
    ſammen
    -0.56
    POSITIVE LOGITS
    Multi
    0.39
    COVID
    0.37
    Note
    0.37
     COVID
    0.35
    multi
    0.35
     stylish
    0.35
    Nice
    0.34
    NOTE
    0.34
     gorgeous
    0.34
     multi
    0.33
    Act Density 0.015%

    No Known Activations