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

    Neuronpedia

    INDEX
    Explanations

    (0,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شرطونه
    0.72
    MinIntensity
    0.68
    kfollowers
    0.66
    𝚖
    0.66
    ip
    0.64
    मेस्टर
    0.63
    ၀၀
    0.63
    icides
    0.62
    нэ
    0.62
    oglobine
    0.61
    POSITIVE LOGITS
    2
    0.80
    ↵↵
    0.79
    "
    0.74
    (
    0.74
    0.71
     and
    0.70
     be
    0.69
    。
    0.63
    The
    0.63
     on
    0.61
    Act Density 0.017%

    No Known Activations