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

    Neuronpedia

    INDEX
    Explanations

    exemption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    璆
    -0.07
     Laf
    -0.07
    <boost
    -0.07
    lb
    -0.07
     UIAlert
    -0.07
    .Enums
    -0.06
    .Library
    -0.06
     serde
    -0.06
    PIP
    -0.06
    fed
    -0.06
    POSITIVE LOGITS
    🐫
    0.08
    窄
    0.08
    ┲
    0.07
    职工
    0.07
    召
    0.07
     traditional
    0.07
     maps
    0.07
     discussions
    0.07
     logo
    0.07
    	model
    0.07
    Act Density 0.019%

    No Known Activations