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

    Neuronpedia

    INDEX
    Explanations

    winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foe
    -0.07
     hứ
    -0.06
     채
    -0.06
     lãi
    -0.06
    ckså
    -0.06
     Hz
    -0.06
    也有
    -0.06
     nedir
    -0.06
    }/>
    -0.06
     спросил
    -0.06
    POSITIVE LOGITS
     winning
    0.32
     Winning
    0.20
    -winning
    0.13
    inning
    0.09
     winnings
    0.08
    _phys
    0.08
     Winners
    0.08
    새
    0.07
     expanding
    0.07
     rés
    0.06
    Act Density 0.003%

    No Known Activations