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

    Neuronpedia

    INDEX
    Explanations

    taxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     миним
    -0.07
     Bolton
    -0.07
     yani
    -0.07
    ［
    -0.07
    ičky
    -0.06
     topping
    -0.06
     parity
    -0.06
    達
    -0.06
    číta
    -0.06
    -find
    -0.06
    POSITIVE LOGITS
    _dec
    0.06
    .Comment
    0.06
    INV
    0.06
     мил
    0.06
     barrel
    0.06
     snapchat
    0.06
     白
    0.06
     Tigers
    0.06
     systematic
    0.06
    ılacak
    0.06
    Act Density 0.017%

    No Known Activations