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

    Neuronpedia

    INDEX
    Explanations

    Code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joking
    -0.06
    олет
    -0.06
     pItem
    -0.06
    ivant
    -0.06
    "x
    -0.06
     وأن
    -0.06
    Found
    -0.06
    :<?
    -0.06
    �이
    -0.06
    baru
    -0.06
    POSITIVE LOGITS
     Gaut
    0.07
     Tyr
    0.07
     Rum
    0.07
     contrat
    0.07
     Astro
    0.06
     standby
    0.06
     Architecture
    0.06
     Crystal
    0.06
     Fast
    0.06
    uma
    0.06
    Act Density 0.000%

    No Known Activations