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

    Neuronpedia

    INDEX
    Explanations

    structured formatting elements, particularly in legal documents

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

    numbered paragraph markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.78
    CloseOperation
    -0.71
    ConstraintMaker
    -0.68
    Chham
    -0.61
     мәкал
    -0.60
    ፩
    -0.60
    RetentionPolicy
    -0.60
    ImageContext
    -0.59
    ьажоргаш
    -0.57
    󠁣
    -0.57
    POSITIVE LOGITS
    Kaieteur
    0.34
    PhysRevLett
    0.33
     narrative
    0.32
    脚注の使い方
    0.32
     garçons
    0.30
    Hintergrund
    0.29
     kök
    0.28
     narrativa
    0.28
     ujarnya
    0.28
     verhaal
    0.28
    Act Density 0.064%

    No Known Activations