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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    因为
    -0.07
    Be
    -0.07
     Bedford
    -0.06
    unicorn
    -0.06
    цез
    -0.06
     overseeing
    -0.06
    िशत
    -0.06
     foolish
    -0.06
     squarely
    -0.06
    tility
    -0.06
    POSITIVE LOGITS
    /System
    0.07
    ambi
    0.06
    >(
    0.06
     CrossAxisAlignment
    0.06
     YouTube
    0.06
     Rear
    0.06
    Wer
    0.06
    ($"{
    0.06
     aboard
    0.06
     están
    0.06
    Act Density 0.034%

    No Known Activations