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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ettir
    -0.07
    ,j
    -0.07
     hebben
    -0.06
     besser
    -0.06
     cushions
    -0.06
    ाथ
    -0.06
    关闭
    -0.06
     adulte
    -0.06
     hora
    -0.06
    aires
    -0.06
    POSITIVE LOGITS
     عدد
    0.06
    islav
    0.06
    -shirts
    0.06
    enders
    0.06
    ImageSharp
    0.06
     Shades
    0.06
     defend
    0.06
    μπ
    0.06
     charm
    0.06
     pendant
    0.06
    Act Density 0.347%

    No Known Activations