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

    Neuronpedia

    INDEX
    Explanations

    Descriptive document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вихов
    -0.07
    -txt
    -0.06
     dist
    -0.06
    _com
    -0.06
     anger
    -0.06
    řil
    -0.06
    -ind
    -0.06
    Random
    -0.06
    險
    -0.06
    /com
    -0.06
    POSITIVE LOGITS
    وط
    0.07
    ========
    0.07
    LOAT
    0.06
     carniv
    0.06
     územ
    0.06
     yapılacak
    0.06
    ائر
    0.06
     QtAws
    0.06
    ---------------↵
    0.06
     Carl
    0.06
    Act Density 0.721%

    No Known Activations