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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Justice
    -0.08
     Justice
    -0.08
     justice
    -0.08
     bravery
    -0.08
     Medic
    -0.08
    Medic
    -0.08
     CONSE
    -0.08
     resonate
    -0.08
     Sheriff
    -0.07
     medicinal
    -0.07
    POSITIVE LOGITS
     četiri
    0.08
    .Send
    0.08
     QU
    0.08
    πα
    0.08
     ચાર
    0.08
     janu
    0.08
    -t
    0.07
     നാല്
    0.07
     നാല
    0.07
    ీస్
    0.07
    Act Density 0.002%

    No Known Activations