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

    Neuronpedia

    INDEX
    Explanations

    promises, injury, how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जरिए
    0.50
     مكت
    0.48
     Radi
    0.47
     Facilities
    0.47
     Knitting
    0.46
     По
    0.45
     Frühstück
    0.45
     शुरूआत
    0.45
     Rear
    0.45
     лекар
    0.44
    POSITIVE LOGITS
     pathogenicity
    0.59
    AllFilesIn
    0.54
     asterisk
    0.50
    פל
    0.50
    ৫
    0.49
     intruders
    0.48
     allegiance
    0.48
    ಐ
    0.48
    чення
    0.47
    มาชิก
    0.45
    Act Density 0.000%

    No Known Activations