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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     threads
    -0.06
    AIT
    -0.06
    いう
    -0.06
     pourrait
    -0.06
    очь
    -0.06
    徐
    -0.06
    	N
    -0.06
     мех
    -0.06
    	t
    -0.06
    еком
    -0.06
    POSITIVE LOGITS
     gerçekleştir
    0.07
     заболевания
    0.07
     PSP
    0.07
     грав
    0.07
    oby
    0.06
     ©
    0.06
     Riy
    0.06
     fulfillment
    0.06
     RS
    0.06
    pez
    0.06
    Act Density 0.001%

    No Known Activations