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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lebih
    -0.07
     out
    -0.06
     harvesting
    -0.06
    Christian
    -0.06
    하여
    -0.06
    ,X
    -0.06
     enjoyed
    -0.06
    owner
    -0.06
    har
    -0.06
    อท
    -0.06
    POSITIVE LOGITS
    Orden
    0.06
    aryana
    0.06
    azen
    0.06
     日本
    0.06
     ipsum
    0.06
    prom
    0.06
    合
    0.06
     Telefon
    0.06
     pris
    0.06
    cente
    0.06
    Act Density 0.009%

    No Known Activations