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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving fractions and functions

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

    Mathematical/Scientific notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation with variables and exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setAccessible
    -0.54
     autorytatywna
    -0.51
     Sommers
    -0.50
    Clik
    -0.49
    ZZZZ
    -0.48
    andre
    -0.48
    ánd
    -0.48
    GEBURTSDATUM
    -0.47
    wers
    -0.47
    Tradu
    -0.46
    POSITIVE LOGITS
    ftagPool
    0.61
    +:+
    0.61
    izr
    0.60
     Sa
    0.54
    cshtml
    0.52
    MemoryWarning
    0.51
     mẽ
    0.51
    Produzione
    0.51
    SBATCH
    0.50
     Sc
    0.49
    Act Density 2.394%

    No Known Activations