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

    Neuronpedia

    INDEX
    Explanations

    requires luck and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    并且
    0.41
     wobei
    0.40
    但是
    0.39
    𝚒
    0.38
    audi
    0.38
    iam
    0.37
     ghost
    0.37
     தேர்த
    0.37
     ked
    0.36
     whereby
    0.36
    POSITIVE LOGITS
     Sore
    0.42
     প্রয়
    0.39
    Planning
    0.39
     COMPOUNDS
    0.39
    Networks
    0.39
     সিদ্ধান্ত
    0.39
     оригіналу
    0.38
     coronary
    0.38
     Planung
    0.38
    鐙
    0.38
    Act Density 0.001%

    No Known Activations