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

    Neuronpedia

    INDEX
    Explanations

    flags and colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -com
    -0.08
    degree
    -0.07
    �
    -0.07
     beginners
    -0.07
     ResourceManager
    -0.07
     Training
    -0.07
    (hand
    -0.07
     Verde
    -0.06
     quả
    -0.06
    围棋
    -0.06
    POSITIVE LOGITS
    热销
    0.07
    .setEditable
    0.07
    巴拉
    0.07
    ALLED
    0.07
     Jr
    0.07
     acl
    0.07
    accessible
    0.06
     rally
    0.06
     anunci
    0.06
    درك
    0.06
    Act Density 0.107%

    No Known Activations