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

    Neuronpedia

    INDEX
    Explanations

    help with assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thể
    0.40
    ographs
    0.37
     }^{*}$
    0.37
    пка
    0.37
    unicaciones
    0.37
    வுக்கு
    0.36
    ਰਾ
    0.36
    ної
    0.35
     जिसने
    0.35
     рабочей
    0.34
    POSITIVE LOGITS
     đỡ
    0.78
     defray
    0.68
    fully
    0.63
     solve
    0.60
     facilitate
    0.59
     navigate
    0.58
     stabilise
    0.54
     alleviate
    0.54
     mitigate
    0.53
     stabilize
    0.53
    Act Density 0.027%

    No Known Activations