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

    Neuronpedia

    INDEX
    Explanations

    list description or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ag
    0.60
    us
    0.60
    ac
    0.59
     কষ্টে
    0.52
    ah
    0.51
    oh
    0.51
    ze
    0.51
    isn
    0.49
    ัน
    0.49
    an
    0.48
    POSITIVE LOGITS
    1
    0.74
    s
    0.71
    \
    0.63
    /
    0.58
     engender
    0.57
     by
    0.55
    Υ
    0.55
     throng
    0.54
     plaques
    0.53
     gel
    0.51
    Act Density 0.000%

    No Known Activations