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

    Neuronpedia

    INDEX
    Explanations

    greetings, results, criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鱈
    0.40
    وهات
    0.39
    textbf
    0.38
     spoken
    0.38
    ালের
    0.37
    ريبي
    0.37
    であることを
    0.37
    洱
    0.37
     রি
    0.36
    獗
    0.36
    POSITIVE LOGITS
     prok
    0.41
     fant
    0.39
    慾
    0.38
     havoc
    0.38
    ผ่น
    0.38
    :%
    0.37
     Fonbet
    0.37
     Honors
    0.36
    do
    0.35
     Mhm
    0.35
    Act Density 0.001%

    No Known Activations