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

    Neuronpedia

    INDEX
    Explanations

    batch file set command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ittet
    0.40
     توص
    0.39
     goss
    0.38
     fonctionnal
    0.38
     Manual
    0.36
    اویز
    0.36
     fram
    0.36
     Administración
    0.36
    Manual
    0.35
     bypass
    0.35
    POSITIVE LOGITS
     set
    0.41
    кін
    0.40
    oncé
    0.40
     neut
    0.40
    कारी
    0.39
     सेट
    0.39
    enegro
    0.38
    uptools
    0.38
    leng
    0.37
    िएको
    0.37
    Act Density 0.004%

    No Known Activations