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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     né
    -0.07
     cooks
    -0.07
    反应
    -0.06
     nád
    -0.06
    ัว
    -0.06
    _CONSTANT
    -0.06
    用户名
    -0.06
     ents
    -0.06
     initiate
    -0.06
     dikkate
    -0.06
    POSITIVE LOGITS
    üsseldorf
    0.07
    (error
    0.06
    smarty
    0.06
    GO
    0.06
    593
    0.06
     WPARAM
    0.06
    -U
    0.06
     jj
    0.06
    Beh
    0.06
     Workflow
    0.06
    Act Density 0.008%

    No Known Activations