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

    Neuronpedia

    INDEX
    Explanations

    collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    warnings
    -0.08
     Grad
    -0.07
     Ikke
    -0.07
     põ
    -0.07
    enz
    -0.07
     Bihar
    -0.07
     ike
    -0.07
     winding
    -0.07
    klin
    -0.07
     Wies
    -0.07
    POSITIVE LOGITS
     rustic
    0.09
     लक
    0.08
    豪
    0.08
     ग्रामीण
    0.08
     compacto
    0.08
     компакт
    0.07
     appet
    0.07
     상품
    0.07
     präsentiert
    0.07
    -carousel
    0.07
    Act Density 0.001%

    No Known Activations