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
     عبد
    -0.06
    procs
    -0.06
     сни
    -0.06
    app
    -0.06
     chứa
    -0.06
     Yosh
    -0.06
    	ob
    -0.06
    황
    -0.06
     номер
    -0.06
     champagne
    -0.06
    POSITIVE LOGITS
    225
    0.07
    нику
    0.07
    ského
    0.07
    \Input
    0.06
    iterator
    0.06
    .Iterator
    0.06
    ераль
    0.06
    نا
    0.06
     primal
    0.06
    erseniz
    0.06
    Act Density 0.010%

    No Known Activations