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

    Neuronpedia

    INDEX
    Explanations

    code syntax and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    垚
    0.43
    Pair
    0.38
     Along
    0.38
     Rather
    0.38
     செல்லும்
    0.38
    agy
    0.37
    Adopt
    0.37
     Char
    0.36
    pair
    0.35
    様に
    0.35
    POSITIVE LOGITS
     doen
    0.40
     potřeb
    0.39
    🇪
    0.39
     eten
    0.38
     fühlen
    0.38
     ইন্দ
    0.38
     diabet
    0.38
     நல
    0.38
    杏
    0.37
    🙆
    0.36
    Act Density 0.032%

    No Known Activations