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

    Neuronpedia

    INDEX
    Explanations

    github repositories sindresorhus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ebiliriz
    -0.08
    yle
    -0.07
    _iteration
    -0.07
    YLE
    -0.07
     ترجمه
    -0.07
    ‌باشد
    -0.06
     TWO
    -0.06
     oluyor
    -0.06
    OVER
    -0.06
     Fucking
    -0.06
    POSITIVE LOGITS
     assassination
    0.07
    (\$
    0.06
    bservable
    0.06
     tq
    0.06
    dbname
    0.06
    textTheme
    0.06
    DIC
    0.06
    ―
    0.06
     παρ
    0.06
     Swal
    0.06
    Act Density 0.000%

    No Known Activations