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

    Neuronpedia

    INDEX
    Explanations

    numerical references or rankings related to acceptable behaviors in a professional context

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

    Numbers followed by a period

    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
     uParam
    -0.84
    }$​
    -0.80
    CppCodeGen
    -0.79
    addCriterion
    -0.76
    apimachinery
    -0.76
     تضيفلها
    -0.75
    rawDesc
    -0.75
     rhestr
    -0.74
    RegressionTest
    -0.74
    JsonHelper
    -0.73
    POSITIVE LOGITS
     cref
    0.54
    8
    0.52
    9
    0.51
     disponibilités
    0.48
    0
    0.47
    7
    0.46
    5
    0.46
    4
    0.45
    6
    0.44
    InstanceState
    0.44
    Act Density 0.044%

    No Known Activations