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

    Neuronpedia

    INDEX
    Explanations

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ktor
    -0.07
    を受
    -0.07
    とう
    -0.06
     Sal
    -0.06
     också
    -0.06
     سفید
    -0.06
     Patrick
    -0.06
     男
    -0.06
     bz
    -0.06
     الفر
    -0.06
    POSITIVE LOGITS
    /Grid
    0.07
    -training
    0.07
    election
    0.07
     shrine
    0.07
    �
    0.06
     irrigation
    0.06
    .Amount
    0.06
     handle
    0.06
     temperature
    0.06
    stin
    0.06
    Act Density 0.020%

    No Known Activations