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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μερα
    -0.07
    comm
    -0.06
    Mas
    -0.06
    beiter
    -0.06
    -0.06
    (\'
    -0.06
    ‘
    -0.06
     banyak
    -0.06
     tercer
    -0.06
     slik
    -0.06
    POSITIVE LOGITS
     обеспеч
    0.07
    -how
    0.07
     intuit
    0.07
    86
    0.06
    yle
    0.06
    198
    0.06
     Orient
    0.06
    Web
    0.06
    Le
    0.06
     dwell
    0.06
    Act Density 0.000%

    No Known Activations