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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    business
    0.40
     ২০২২
    0.39
     broader
    0.39
    পুরে
    0.38
    regex
    0.38
     २०२२
    0.38
    LightTheme
    0.37
    Microelectronics
    0.37
     protons
    0.36
    quia
    0.36
    POSITIVE LOGITS
    xymatrix
    0.48
     labelling
    0.47
     labeling
    0.43
    0.43
     ਕੇ
    0.41
    
    0.40
     מס
    0.40
     화면
    0.40
     rimane
    0.39
    關鍵
    0.39
    Act Density 0.000%

    No Known Activations