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

    Neuronpedia

    INDEX
    Explanations

    integumentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    1.38
    ።
    1.30
    ３
    1.12
     Бүгенге
    1.08
    ാര്യ
    1.07
     ۳
    1.06
    ukuran
    1.05
     crucified
    1.05
    سی
    1.03
    aucune
    1.03
    POSITIVE LOGITS
    0
    1.21
    l
    1.09
     In
    1.02
    ors
    1.02
    1.01
    í
    1.00
     The
    0.99
     It
    0.98
    ă
    0.95
    és
    0.94
    Act Density 0.000%

    No Known Activations