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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OWN
    -0.07
     Elias
    -0.07
     cánh
    -0.07
     xe
    -0.06
    	signal
    -0.06
     Uz
    -0.06
    cache
    -0.06
     blok
    -0.06
     loft
    -0.06
     Constant
    -0.06
    POSITIVE LOGITS
    (firstName
    0.07
     DERP
    0.06
    �
    0.06
    imir
    0.06
    arking
    0.06
     gratuites
    0.06
     đối
    0.06
    _UNSUPPORTED
    0.06
    phys
    0.06
     устанавлива
    0.06
    Act Density 0.000%

    No Known Activations