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

    Neuronpedia

    INDEX
    Explanations

    a really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucker
    0.82
     CBIT
    0.77
     Cess
    0.75
    CMI
    0.73
    canny
    0.71
     Emeritus
    0.69
     Macc
    0.69
    Muse
    0.68
    emics
    0.68
    錳
    0.67
    POSITIVE LOGITS
     Ra
    1.08
     RING
    1.03
    Ra
    1.01
     Ring
    1.00
    Ring
    0.99
    Transaction
    0.99
     Rings
    0.97
     Bang
    0.97
     Rolf
    0.95
     ring
    0.95
    Act Density 2.926%

    No Known Activations