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

    Neuronpedia

    INDEX
    Explanations

    ?”

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wygląda
    -0.07
     geliş
    -0.07
    .department
    -0.07
    ليس
    -0.07
     Bit
    -0.07
    itto
    -0.07
    ucha
    -0.07
    .rabbit
    -0.07
    เดอะ
    -0.06
    abbit
    -0.06
    POSITIVE LOGITS
    就把
    0.08
    xies
    0.07
     assumes
    0.07
     Beacon
    0.07
     included
    0.07
     serum
    0.07
     Took
    0.07
     valuation
    0.07
    显著
    0.07
     shown
    0.07
    Act Density 0.025%

    No Known Activations