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

    Neuronpedia

    INDEX
    Explanations

    ex

    np_max-act · gemini-2.0-flash

    tokens that are parts of institutional mailing-address blocks (postal-code/cedex-like fragments and adjacent numeric address pieces).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Number
    -0.07
    检
    -0.07
     number
    -0.07
     распростран
    -0.07
     numbers
    -0.07
    trag
    -0.07
     PLACE
    -0.06
    戦
    -0.06
     Temple
    -0.06
    のに
    -0.06
    POSITIVE LOGITS
    orio
    0.06
     dossier
    0.06
     glossy
    0.06
    á
    0.05
    .session
    0.05
    lude
    0.05
    promo
    0.05
    �
    0.05
    ีโอ
    0.05
     searcher
    0.05
    Act Density 0.001%

    No Known Activations