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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    印章
    -0.08
    넓
    -0.07
     Dự
    -0.07
    aal
    -0.07
    总队
    -0.07
    -cloud
    -0.07
     depth
    -0.06
     Elsa
    -0.06
     والذي
    -0.06
    .convert
    -0.06
    POSITIVE LOGITS
    جرائم
    0.07
    asing
    0.07
    etrics
    0.07
    	point
    0.07
     Keystone
    0.07
     oblig
    0.07
    עמי
    0.07
    Laughs
    0.07
    ℝ
    0.07
     ?:
    0.06
    Act Density 0.030%

    No Known Activations