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

    Neuronpedia

    INDEX
    Explanations

    Dynamic relationships and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    મિંગ
    0.38
     রোধ
    0.38
    വില്‍
    0.37
    usso
    0.37
     corris
    0.37
    👆
    0.35
    lich
    0.35
    🥣
    0.35
    笘
    0.35
    otle
    0.34
    POSITIVE LOGITS
     predstav
    0.40
     Dynamic
    0.40
    IFT
    0.39
    Dynamic
    0.38
     cosmopolitan
    0.38
     Roland
    0.38
     Complexity
    0.37
     Electric
    0.37
     Cré
    0.37
     dynamic
    0.37
    Act Density 0.001%

    No Known Activations