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

    Neuronpedia

    INDEX
    Explanations

    minority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ed
    -0.07
    uale
    -0.07
    ca
    -0.07
    Setup
    -0.06
    .location
    -0.06
    욯
    -0.06
     re
    -0.06
    
    -0.06
     ca
    -0.06
    af
    -0.06
    POSITIVE LOGITS
     rozp
    0.07
     ראשון
    0.07
     nhờ
    0.07
     بنسبة
    0.07
    <Rigidbody
    0.07
     bargaining
    0.07
    浊
    0.07
    .drawString
    0.07
    猇
    0.07
    �
    0.07
    Act Density 0.007%

    No Known Activations