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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devant
    -0.07
    icine
    -0.07
     downloader
    -0.07
     punch
    -0.06
     fich
    -0.06
     Ezek
    -0.06
     Blob
    -0.06
    ोई
    -0.06
     Tk
    -0.06
    Picker
    -0.06
    POSITIVE LOGITS
    )tableView
    0.07
    monton
    0.07
    FunctionFlags
    0.06
     ร
    0.06
    _ENABLED
    0.06
     联
    0.06
     Uns
    0.06
    純
    0.06
    710
    0.06
    лон
    0.06
    Act Density 0.001%

    No Known Activations