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

    Neuronpedia

    INDEX
    Explanations

    say "public"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buster
    -0.08
     prostitutes
    -0.07
    ीप
    -0.07
     như
    -0.07
    omorphic
    -0.07
     methodName
    -0.07
    ......
    -0.07
    شتر
    -0.06
     flashy
    -0.06
    ;d
    -0.06
    POSITIVE LOGITS
    .EventSystems
    0.06
     asteroid
    0.06
     cir
    0.06
    30
    0.06
     lip
    0.06
     Kath
    0.06
    ระบบ
    0.06
    illiseconds
    0.06
    44
    0.06
     나오
    0.06
    Act Density 0.019%

    No Known Activations