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

    Neuronpedia

    INDEX
    Explanations

    matrix-related terms and operations

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

    matrix operations and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.34
    érale
    -0.34
    EC
    -0.33
     isolado
    -0.33
    Cover
    -0.32
     visitare
    -0.32
     colorida
    -0.32
     simplifié
    -0.32
     incluidas
    -0.32
    Παραπομπές
    -0.31
    POSITIVE LOGITS
    EndContext
    0.60
     pleaſure
    0.59
    onSubmit
    0.56
    Derbyniad
    0.55
    Rüyada
    0.53
     '\\;'
    0.53
    ParallelGroup
    0.52
     تضيفلها
    0.51
    FunctionFlags
    0.50
     насеље
    0.50
    Act Density 0.410%

    No Known Activations