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

    Neuronpedia

    INDEX
    Explanations

    language terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repayments
    -0.09
     bango
    -0.08
     Unterricht
    -0.08
     debit
    -0.07
    -confidence
    -0.07
     Dys
    -0.07
     공연
    -0.07
     Debit
    -0.07
     studenti
    -0.07
     Integrity
    -0.07
    POSITIVE LOGITS
    aken
    0.07
    šķ
    0.07
     expans
    0.07
     говоря
    0.07
    副
    0.07
    版
    0.07
    ache
    0.07
     pren
    0.07
    Queues
    0.07
    Patent
    0.07
    Act Density 0.008%

    No Known Activations