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

    Neuronpedia

    INDEX
    Explanations

    capturing subprocess output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AudioClip
    0.46
     電気
    0.42
    ()],
    0.42
    ಬೇಕು
    0.42
    selfobj
    0.40
    izma
    0.40
    LogProfile
    0.40
     என்கிறார்
    0.39
    schule
    0.39
    yship
    0.39
    POSITIVE LOGITS
     беше
    0.42
     roto
    0.37
    dah
    0.37
    ARDO
    0.37
     प्रदर्शन
    0.36
    disc
    0.36
     νέα
    0.36
     Ged
    0.35
     hade
    0.35
     csal
    0.35
    Act Density 0.001%

    No Known Activations