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

    Neuronpedia

    INDEX
    Explanations

    holding power button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ```
    0.42
    obs
    0.42
     ``
    0.40
    ando
    0.38
    itake
    0.37
    mu
    0.37
     Bits
    0.37
     Coefficients
    0.37
     Rows
    0.37
     LiDAR
    0.36
    POSITIVE LOGITS
     citt
    0.39
     সম্পদ
    0.39
     څه
    0.38
    ArchiveAction
    0.38
     প্রয়োজন
    0.36
     palate
    0.36
     môn
    0.35
     qualit
    0.35
     trai
    0.35
     bein
    0.35
    Act Density 0.000%

    No Known Activations