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

    Neuronpedia

    INDEX
    Explanations

    breaking down concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    КА
    0.49
    निवेश
    0.47
    도
    0.44
    에
    0.43
     praia
    0.43
     timepiece
    0.43
     galería
    0.42
     uninterrupted
    0.42
    гія
    0.42
    ло
    0.41
    POSITIVE LOGITS
     SWAT
    0.44
     Iowa
    0.44
     চালানো
    0.44
    iterations
    0.44
    0.44
    getConfig
    0.44
    agonal
    0.43
     CRISPR
    0.43
    lings
    0.43
     Kentucky
    0.42
    Act Density 0.019%

    No Known Activations