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

    Neuronpedia

    INDEX
    Explanations

    money in politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เขต
    -0.06
    .matmul
    -0.06
     boh
    -0.06
    teří
    -0.06
    /results
    -0.06
     بازیگر
    -0.06
     almış
    -0.06
     усіх
    -0.05
     přesně
    -0.05
     Ris
    -0.05
    POSITIVE LOGITS
     Iraq
    0.08
    identity
    0.07
     fake
    0.07
     Node
    0.07
    abel
    0.07
    ーク
    0.07
    alling
    0.07
     stores
    0.06
     CW
    0.06
     ming
    0.06
    Act Density 0.007%

    No Known Activations