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

    Neuronpedia

    INDEX
    Explanations

    typescript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commas
    -0.08
     Fest
    -0.07
     amt
    -0.07
    monds
    -0.07
     oud
    -0.07
     Voll
    -0.07
    _dev
    -0.07
    _buffers
    -0.07
    ammed
    -0.07
    akte
    -0.07
    POSITIVE LOGITS
     />
    0.08
    시스템
    0.07
    rik
    0.07
    手下
    0.07
    Line
    0.06
     alteration
    0.06
    ificates
    0.06
    SPA
    0.06
     fırsat
    0.06
     diseño
    0.06
    Act Density 0.003%

    No Known Activations