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

    Neuronpedia

    INDEX
    Explanations

    ational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    濠
    -0.09
    Jeremy
    -0.07
    inne
    -0.07
    Ý
    -0.07
     spanning
    -0.07
    ={['
    -0.07
    葡京
    -0.07
    .$
    -0.07
    unto
    -0.06
    琼
    -0.06
    POSITIVE LOGITS
     oi
    0.07
     explained
    0.07
    ليس
    0.07
     dl
    0.07
    铽
    0.07
    orias
    0.07
     settlements
    0.07
     araştırma
    0.07
    Dragon
    0.06
     Policies
    0.06
    Act Density 0.002%

    No Known Activations