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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trustees
    -0.08
     cha
    -0.07
    ).</
    -0.07
     WhatsApp
    -0.07
    лекс
    -0.07
    ADIO
    -0.06
     winters
    -0.06
    Root
    -0.06
     DOS
    -0.06
     WELL
    -0.06
    POSITIVE LOGITS
     özel
    0.06
     disciplinary
    0.06
     functools
    0.06
     případě
    0.06
     مهد
    0.06
    جاج
    0.06
    Stencil
    0.06
     approached
    0.06
     listing
    0.06
    基地
    0.06
    Act Density 0.016%

    No Known Activations