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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uniform
    -0.07
     در
    -0.06
     Sacred
    -0.06
     bunny
    -0.06
    ínu
    -0.06
     ایران
    -0.06
     cũng
    -0.06
     forall
    -0.06
     substant
    -0.06
    росто
    -0.06
    POSITIVE LOGITS
     Mos
    0.07
     areas
    0.06
     程
    0.06
    èmes
    0.06
    ossed
    0.06
     Oriental
    0.06
     area
    0.06
     authorities
    0.06
    Pago
    0.06
     ";↵
    0.06
    Act Density 0.011%

    No Known Activations