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

    Neuronpedia

    INDEX
    Explanations

    memory usage, management, issues, leaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ми
    0.91
    。\
    0.85
    。
    0.77
    ंगर
    0.77
    மாக
    0.76
     места
    0.76
     леса
    0.74
    𝐨
    0.73
     meagre
    0.73
    мато
    0.72
    POSITIVE LOGITS
    X
    0.94
    us
    0.88
    ↵
    0.86
    L
    0.86
    H
    0.86
    R
    0.85
    A
    0.84
     that
    0.83
    T
    0.83
    C
    0.81
    Act Density 0.012%

    No Known Activations