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

    Neuronpedia

    INDEX
    Explanations

    meet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Where
    -0.08
     популяр
    -0.07
     Posts
    -0.07
    енности
    -0.06
     reservations
    -0.06
    static
    -0.06
    prod
    -0.06
     vulnerabilities
    -0.06
    ortality
    -0.06
     wandering
    -0.06
    POSITIVE LOGITS
     فرزند
    0.07
    _TIM
    0.06
     widening
    0.06
     Imp
    0.06
     cambiar
    0.06
     春
    0.06
    .setColumn
    0.06
    yc
    0.06
     Compatible
    0.06
     McCarthy
    0.06
    Act Density 0.029%

    No Known Activations