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

    Neuronpedia

    INDEX
    Explanations

    punctuation patterns and structural elements within a document

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

    references and conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.73
    RegressionTest
    -0.62
     MonoBehaviour
    -0.58
    Ɓ
    -0.56
    MessageTagHelper
    -0.56
     kaarangay
    -0.54
    TagNumber
    -0.54
    Autoritní
    -0.54
     onResponse
    -0.52
     BaseActivity
    -0.50
    POSITIVE LOGITS
    newtheorem
    0.85
     незавершена
    0.45
     çap
    0.36
    ValueStyle
    0.35
    Související
    0.34
     Cię
    0.33
    enumi
    0.33
    guenos
    0.32
    BorderFactory
    0.32
    Dichlorobenzene
    0.32
    Act Density 0.003%

    No Known Activations