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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and mathematical symbols associated with statistical or probabilistic models

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

    Numbers followed by periods or commas

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    จบ
    -0.54
    ISCH
    -0.52
    AVES
    -0.51
    CppMethod
    -0.51
    ámico
    -0.49
    proportion
    -0.49
    ❮
    -0.49
    ichier
    -0.49
    knex
    -0.47
    ÉM
    -0.47
    POSITIVE LOGITS
     }},
    0.67
     kasarigan
    0.67
    ?,
    0.66
    ,
    0.65
     avoient
    0.64
     、
    0.61
     étoit
    0.60
    NameInMap
    0.60
    、
    0.58
    >,</
    0.58
    Act Density 0.692%

    No Known Activations