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

    Neuronpedia

    INDEX
    Explanations

    location, shape, and distributed concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нове
    0.54
    ская
    0.49
    udier
    0.48
    rétaire
    0.48
     Meille
    0.45
    τά
    0.45
    ссажи
    0.45
    rī
    0.45
    ского
    0.45
    пла
    0.44
    POSITIVE LOGITS
    ANA
    0.54
    bpm
    0.53
    IDS
    0.53
     едно
    0.52
    MS
    0.50
    SN
    0.48
    MSA
    0.48
    in
    0.48
    MMM
    0.47
    JK
    0.46
    Act Density 0.000%

    No Known Activations