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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.18
     parameter
    0.18
    graphHead
    0.18
     syllable
    0.18
     substring
    0.17
    rafpunkte
    0.17
     thisTrial
    0.17
     ១
    0.17
     dimensionless
    0.17
    AutoStabilise
    0.17
    POSITIVE LOGITS
     and
    0.28
    and
    0.26
    और
    0.24
     ಮತ್ತು
    0.24
     the
    0.23
    the
    0.23
     மற்றும்
    0.22
     và
    0.21
     और
    0.21
     которые
    0.21
    Act Density 4.928%

    No Known Activations