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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éry
    -0.07
     belt
    -0.07
     ActionType
    -0.06
    uddenly
    -0.06
    ))[
    -0.06
    モン
    -0.06
     loudly
    -0.06
    istle
    -0.06
     supervise
    -0.06
     tightened
    -0.06
    POSITIVE LOGITS
     الكه
    0.08
    παίδ
    0.07
    ใคร
    0.07
    であり
    0.07
     Amen
    0.06
    RowAt
    0.06
     Mitgli
    0.06
     Rubin
    0.06
     Wochen
    0.06
     SVN
    0.06
    Act Density 0.038%

    No Known Activations