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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _scripts
    -0.07
    Los
    -0.06
     Kad
    -0.06
    uenta
    -0.06
     Halloween
    -0.06
     увер
    -0.06
     Providence
    -0.06
    Miss
    -0.06
     Slayer
    -0.06
    AllWindows
    -0.06
    POSITIVE LOGITS
     öncelik
    0.07
     biraz
    0.06
    wow
    0.06
     WoW
    0.06
     '#
    0.06
    /remove
    0.06
     收
    0.06
     Conversation
    0.06
     (#
    0.06
     بص
    0.06
    Act Density 0.031%

    No Known Activations