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

    Neuronpedia

    INDEX
    Explanations

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    controllers
    -0.10
     المن
    -0.07
     fixtures
    -0.07
     "#"
    -0.07
     lead
    -0.06
    _DENIED
    -0.06
    xfc
    -0.06
     Taking
    -0.06
    ADC
    -0.06
    (es
    -0.06
    POSITIVE LOGITS
    截
    0.06
     скры
    0.06
     iT
    0.06
     offsetY
    0.06
    ucing
    0.06
     Kul
    0.06
     neob
    0.06
     również
    0.06
     colore
    0.06
     야
    0.06
    Act Density 0.077%

    No Known Activations