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

    Neuronpedia

    INDEX
    Explanations

    now,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ormai
    0.48
    မျှ
    0.47
     ',
    0.46
     vytvá
    0.45
    ',
    0.45
     mkdir
    0.44
    .'
    0.44
    \",
    0.43
    morph
    0.42
    /',
    0.42
    POSITIVE LOGITS
    p
    0.54
     admittedly
    0.50
    ras
    0.49
    Ｐ
    0.48
    至于
    0.46
    もちろん
    0.45
     cunning
    0.44
     oczywiście
    0.43
    J
    0.43
     confess
    0.42
    Act Density 0.017%

    No Known Activations