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

    Neuronpedia

    INDEX
    Explanations

    mathematical and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стный
    0.40
    raya
    0.39
    star
    0.39
     пород
    0.39
    ிலே
    0.38
    镌
    0.38
    訨
    0.38
    █
    0.37
    [];
    0.37
     ምልክ
    0.37
    POSITIVE LOGITS
     R
    0.39
    αν
    0.39
     uč
    0.39
     группе
    0.39
     indifer
    0.36
     Samp
    0.36
     trainee
    0.35
     проє
    0.35
     proj
    0.35
     York
    0.35
    Act Density 0.003%

    No Known Activations