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

    Neuronpedia

    INDEX
    Explanations

    cycle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Syrian
    -0.09
    nj
    -0.07
    �்
    -0.07
     coupled
    -0.07
     FAIR
    -0.07
     Sarah
    -0.07
    .TIME
    -0.07
     govern
    -0.07
     harmful
    -0.07
    gul
    -0.07
    POSITIVE LOGITS
     winding
    0.09
    交通
    0.09
     formation
    0.08
    Formation
    0.08
     निर्माण
    0.08
     lurking
    0.08
     вида
    0.08
     вокруг
    0.08
     paseo
    0.08
     সৃষ্টি
    0.08
    Act Density 0.007%

    No Known Activations