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

    Neuronpedia

    INDEX
    Explanations

    Questions or lack of understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всю
    -0.06
     manuscript
    -0.06
    圧
    -0.06
     Addison
    -0.06
     Beach
    -0.06
    Pizza
    -0.06
     removeFrom
    -0.06
     С
    -0.06
     toplum
    -0.06
     KA
    -0.06
    POSITIVE LOGITS
     Ging
    0.07
     phá
    0.07
    icago
    0.06
    .lbl
    0.06
     Stunden
    0.06
    áy
    0.06
     (-
    0.06
    年に
    0.06
    ivor
    0.06
    �
    0.06
    Act Density 0.035%

    No Known Activations