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

    Neuronpedia

    INDEX
    Explanations

    It's about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glitches
    0.42
     hesitated
    0.42
     terl
    0.38
     approximated
    0.37
     elt
    0.37
    াইয়৷
    0.37
     milled
    0.37
     Mö
    0.36
    xia
    0.36
     fratt
    0.36
    POSITIVE LOGITS
     about
    1.55
     tentang
    1.34
    about
    1.30
     عن
    1.28
     About
    1.27
    About
    1.21
     अबाउट
    1.21
     ABOUT
    1.20
     về
    1.18
     apie
    1.14
    Act Density 0.013%

    No Known Activations