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

    Neuronpedia

    INDEX
    Explanations

    references to various theoretical models in scientific contexts

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

    scientific models and their parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (&:
    -0.44
     NVMe
    -0.43
     zelve
    -0.42
    IGENCE
    -0.41
     nemlig
    -0.41
     Cervical
    -0.41
     bureaus
    -0.41
     BEAUTY
    -0.41
    lijck
    -0.40
     faculty
    -0.40
    POSITIVE LOGITS
     model
    0.68
     Model
    0.56
    RegressionTest
    0.56
    ArgumentParser
    0.56
    UnusedPrivate
    0.54
     MODEL
    0.54
    model
    0.53
     arşivlendi
    0.52
    хьтан
    0.49
    BufferException
    0.49
    Act Density 0.056%

    No Known Activations