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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    podob
    -0.07
     /****************************************************************
    -0.07
     лег
    -0.06
    .non
    -0.06
    	My
    -0.06
    δό
    -0.06
     бед
    -0.06
    rie
    -0.06
     specs
    -0.06
    putation
    -0.06
    POSITIVE LOGITS
    continental
    0.07
     台
    0.07
     sizi
    0.07
    .Dictionary
    0.07
    ropical
    0.06
    uppy
    0.06
    Introduced
    0.06
     forgive
    0.06
     descend
    0.06
     Augusta
    0.06
    Act Density 0.001%

    No Known Activations