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

    Neuronpedia

    INDEX
    Explanations

    references to legal sections and sub-sections

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

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.61
     Theſe
    -0.59
     Reſ
    -0.59
    ſelf
    -0.58
     Verſ
    -0.56
     Houſe
    -0.54
     Beſ
    -0.54
    OGND
    -0.51
     Majefty
    -0.51
    Autoritní
    -0.50
    POSITIVE LOGITS
    umbered
    0.36
    amide
    0.36
    RTHOOK
    0.34
     paragraph
    0.32
     paragraphs
    0.30
    jsdelivr
    0.30
     vagas
    0.30
     Coding
    0.30
    AutoField
    0.29
     czo
    0.29
    Act Density 0.406%

    No Known Activations