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

    Neuronpedia

    INDEX
    Explanations

    licensing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _take
    -0.07
    Medical
    -0.07
    oud
    -0.07
     JButton
    -0.06
     підприєм
    -0.06
     interp
    -0.06
    icides
    -0.06
     sunset
    -0.06
    .Background
    -0.06
    Blur
    -0.06
    POSITIVE LOGITS
     MCP
    0.06
     OST
    0.06
    implicitly
    0.06
    mot
    0.06
    言った
    0.06
    北
    0.06
    licative
    0.06
    awaiter
    0.06
    �
    0.06
    iges
    0.06
    Act Density 0.003%

    No Known Activations