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

    Neuronpedia

    INDEX
    Explanations

    ('

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    常见
    -0.07
    quota
    -0.07
    施工
    -0.07
    傣
    -0.07
    多功能
    -0.07
    钢筋
    -0.07
    -spot
    -0.07
    أمن
    -0.07
    amen
    -0.06
     yoga
    -0.06
    POSITIVE LOGITS
    오는
    0.07
    curacy
    0.07
     Giới
    0.07
    分析
    0.06
    扭转
    0.06
     EFF
    0.06
    .Input
    0.06
    '*
    0.06
     עולה
    0.06
     tells
    0.06
    Act Density 0.101%

    No Known Activations