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

    Neuronpedia

    INDEX
    Explanations

    contraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sewage
    -0.07
     OR
    -0.06
     jeopard
    -0.06
    ováno
    -0.06
     getVersion
    -0.06
     Ста
    -0.06
     fö
    -0.06
     Olsen
    -0.06
    üyorum
    -0.06
     dissemination
    -0.06
    POSITIVE LOGITS
     thì
    0.08
     contraction
    0.07
     accept
    0.07
     Subscriber
    0.07
    %).↵↵
    0.07
    connect
    0.07
    (card
    0.07
     Kurd
    0.06
     ترک
    0.06
     }↵↵
    0.06
    Act Density 0.008%

    No Known Activations