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

    Neuronpedia

    INDEX
    Explanations

    Shader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᖱ
    -0.07
     shorts
    -0.07
     Españ
    -0.07
     meanwhile
    -0.06
    瘛
    -0.06
     이
    -0.06
    𫗴
    -0.06
    sold
    -0.06
    ’y
    -0.06
    铃
    -0.06
    POSITIVE LOGITS
     updatedAt
    0.06
    �
    0.06
    imens
    0.06
    про
    0.06
    cheiden
    0.06
     insecure
    0.06
     {}
↵
    0.06
    -M
    0.06
    _shop
    0.06
     ###↵
    0.06
    Act Density 0.002%

    No Known Activations