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

    Neuronpedia

    INDEX
    Explanations

    source links and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homogene
    0.41
     Lerner
    0.38
     homogeneity
    0.37
     정리
    0.37
    lipped
    0.36
    均
    0.36
     adequately
    0.36
    􏰁
    0.36
     odv
    0.36
    亮度
    0.35
    POSITIVE LOGITS
    રમાં
    0.42
     iemand
    0.40
    Brainz
    0.40
     cikin
    0.38
     geï
    0.38
    웹
    0.38
     pomoc
    0.37
    latex
    0.37
     petróleo
    0.37
    цька
    0.37
    Act Density 0.001%

    No Known Activations