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

    Neuronpedia

    INDEX
    Explanations

    lab and synthetic materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穣
    0.55
    ブ
    0.53
    喩
    0.51
    ミ
    0.49
    ানে
    0.49
     conect
    0.48
    が表示
    0.48
    ின
    0.48
    ﻠ
    0.47
    その他
    0.46
    POSITIVE LOGITS
    o
    0.58
    an
    0.57
    dling
    0.56
    ar
    0.55
    in
    0.54
    innov
    0.51
    e
    0.51
    t
    0.50
    f
    0.50
    apse
    0.49
    Act Density 0.001%

    No Known Activations