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

    Neuronpedia

    INDEX
    Explanations

    xor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marche
    -0.08
     грам
    -0.08
     मूल
    -0.08
     وما
    -0.08
     चुका
    -0.07
     auditions
    -0.07
     Amen
    -0.07
     చేర
    -0.07
     Via
    -0.07
    êtres
    -0.07
    POSITIVE LOGITS
     XOR
    0.08
    Resistance
    0.08
    Exclusive
    0.08
    holes
    0.08
    hole
    0.08
     inorganic
    0.07
    �
    0.07
     করলে
    0.07
    _frequency
    0.07
    _result
    0.07
    Act Density 0.003%

    No Known Activations