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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cassert
    -0.07
    ilar
    -0.06
    .printf
    -0.06
    Mrs
    -0.06
    erer
    -0.06
    >s
    -0.06
     bearer
    -0.06
     MenuItem
    -0.06
     Rafael
    -0.06
     otra
    -0.06
    POSITIVE LOGITS
    อม
    0.07
    UNS
    0.07
     ممن
    0.07
    ук
    0.07
    acting
    0.07
    istinguished
    0.07
    sizlik
    0.07
     خد
    0.07
    atom
    0.07
    Gem
    0.07
    Act Density 0.008%

    No Known Activations