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

    Neuronpedia

    INDEX
    Explanations

    indicates continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    倝
    0.74
     سلاټ
    0.66
    িগুণ
    0.60
    賖
    0.60
    ̋
    0.59
    厓
    0.56
    ᄒ
    0.56
     جوسینو
    0.55
    䔉
    0.55
    स्तानी
    0.55
    POSITIVE LOGITS
    ...
    4.97
    …
    4.86
    ….
    4.39
    ....
    4.29
    ……
    4.26
    \...
    4.24
    ...?
    4.21
    ...)
    4.21
    …?
    4.18
    …..
    4.14
    Act Density 0.391%

    No Known Activations