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

    Neuronpedia

    INDEX
    Explanations

    and followed by verb or describes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.91
    ের
    0.85
    માં
    0.76
     بر
    0.74
     ('
    0.70
    。\
    0.69
     ☑
    0.69
     with
    0.68
     by
    0.68
     '~
    0.66
    POSITIVE LOGITS
    มัน
    0.70
     ಏನ
    0.61
    ’
    0.58
    שהו
    0.57
     kiu
    0.56
    ismi
    0.56
    ザ
    0.55
    <0x98>
    0.54
    choline
    0.54
     นิด
    0.54
    Act Density 0.457%

    No Known Activations