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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orent
    -0.08
     Excell
    -0.07
    Correction
    -0.07
     refuge
    -0.06
     Μετα
    -0.06
     sucess
    -0.06
    �
    -0.06
    991
    -0.06
    fa
    -0.06
     送
    -0.06
    POSITIVE LOGITS
    langs
    0.08
     sein
    0.07
     disgusted
    0.06
     вид
    0.06
     ها
    0.06
     spolu
    0.06
    generic
    0.06
     bulky
    0.06
     zd
    0.06
    137
    0.06
    Act Density 0.000%

    No Known Activations