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

    Neuronpedia

    INDEX
    Explanations

    doing something via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంచరీలు
    0.51
     барои
    0.45
    τά
    0.38
    UIAlert
    0.38
    chränk
    0.38
    তই
    0.37
    ിലേ
    0.36
    psie
    0.36
     эсеп
    0.35
    សម្រាប់
    0.35
    POSITIVE LOGITS
     via
    2.39
     באמצעות
    2.39
     poprzez
    2.34
     mediante
    2.28
     pomocí
    2.20
     through
    2.19
     посредством
    2.19
     melalui
    2.16
     tramite
    2.13
     using
    2.05
    Act Density 0.139%

    No Known Activations