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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всю
    -0.07
    不好
    -0.07
     Sap
    -0.06
     versions
    -0.06
    чного
    -0.06
    ू
    -0.06
     czy
    -0.06
    ưu
    -0.06
    щин
    -0.06
     better
    -0.06
    POSITIVE LOGITS
    erral
    0.06
     вересня
    0.06
     operative
    0.06
    abi
    0.06
    765
    0.06
    复
    0.06
    아
    0.06
    (&$
    0.06
     Melanie
    0.05
     absl
    0.05
    Act Density 0.000%

    No Known Activations