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

    Neuronpedia

    INDEX
    Explanations

    division by division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .)..
    0.92
    .!
    0.88
    .):
    0.86
    慎
    0.84
    emes
    0.84
    istaa
    0.84
    .
    0.83
    .).
    0.82
     sentidos
    0.82
    yster
    0.80
    POSITIVE LOGITS
     toep
    0.88
     scholar
    0.86
     গেছেন
    0.83
     imposed
    0.79
     Anlage
    0.78
    +}(
    0.78
     bombed
    0.77
     ചെയ്ത
    0.76
     FBI
    0.75
    |+|
    0.74
    Act Density 0.001%

    No Known Activations