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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     king
    -0.08
     Vill
    -0.07
     conquer
    -0.07
     KING
    -0.07
     inappropriate
    -0.07
     witch
    -0.07
     Hill
    -0.07
    ILLE
    -0.06
     helm
    -0.06
    IconModule
    -0.06
    POSITIVE LOGITS
     data
    0.17
    data
    0.17
     Data
    0.16
    Data
    0.16
    _data
    0.13
    .data
    0.13
     DATA
    0.12
    	data
    0.12
    DATA
    0.12
    =data
    0.12
    Act Density 0.147%

    No Known Activations