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

    Neuronpedia

    INDEX
    Explanations

    decisions and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.11
    THE
    -0.08
     an
    -0.08
     The
    -0.08
     THE
    -0.07
    The
    -0.07
    .The
    -0.07
    ,the
    -0.07
    the
    -0.07
    졌다
    -0.07
    POSITIVE LOGITS
     succes
    0.07
     ورزش
    0.06
     inventive
    0.06
     altro
    0.06
     서울
    0.06
    ([]
    0.06
    -floor
    0.06
     floor
    0.06
    >↵↵↵↵↵
    0.05
     Thirty
    0.05
    Act Density 0.325%

    No Known Activations