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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertext
    -0.07
    特別
    -0.06
     fondo
    -0.06
    eteria
    -0.06
    rak
    -0.06
     segregation
    -0.06
    يف
    -0.06
    १९
    -0.06
     Freak
    -0.06
    sí
    -0.06
    POSITIVE LOGITS
     goes
    0.08
     authorize
    0.07
    "],"
    0.07
    bury
    0.06
     subtotal
    0.06
    ήμερα
    0.06
     DROP
    0.06
     SEA
    0.06
    ousing
    0.06
     REGARD
    0.06
    Act Density 0.025%

    No Known Activations