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

    Neuronpedia

    INDEX
    Explanations

    Streaming/downloading media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Agent
    -0.06
     Ston
    -0.06
    ++;↵
    -0.06
    ού
    -0.06
     tower
    -0.06
    -Fi
    -0.06
     pk
    -0.06
     ann
    -0.06
     nosso
    -0.06
    ognition
    -0.06
    POSITIVE LOGITS
     wording
    0.08
     uphe
    0.07
     aston
    0.06
     womens
    0.06
     возможность
    0.06
    扶
    0.06
     İs
    0.06
    _txn
    0.06
    委員
    0.06
     Added
    0.06
    Act Density 0.067%

    No Known Activations