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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    née
    -0.07
    pell
    -0.07
     tùy
    -0.07
    ụ
    -0.07
    统领
    -0.06
    quat
    -0.06
    かけ
    -0.06
    ừ
    -0.06
    련
    -0.06
     לכ
    -0.06
    POSITIVE LOGITS
    .CheckedChanged
    0.08
     strengths
    0.07
    .SelectedIndexChanged
    0.07
    .form
    0.07
    (delta
    0.07
     Health
    0.07
    还需
    0.07
    建设
    0.07
     conduct
    0.06
    /Form
    0.06
    Act Density 0.001%

    No Known Activations