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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fer
    -0.07
     hor
    -0.07
    Hdr
    -0.07
     Т
    -0.07
     Hann
    -0.07
     вид
    -0.07
     iam
    -0.07
     relay
    -0.07
     scored
    -0.07
    reve
    -0.06
    POSITIVE LOGITS
     السنوات
    0.08
    โบราณ
    0.07
    紀錄
    0.07
    ﹱ
    0.07
     Başkanlığı
    0.07
     mailed
    0.07
     שמורות
    0.07
    坋
    0.07
     realpath
    0.07
    秦皇
    0.06
    Act Density 0.000%

    No Known Activations