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

    Neuronpedia

    INDEX
    Explanations

    summarize, categorize, sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.84
     или
    0.77
     ou
    0.71
     或
    0.70
    /
    0.69
    或是
    0.67
    或
    0.64
     atau
    0.64
     या
    0.63
     otherwise
    0.59
    POSITIVE LOGITS
     definisi
    0.72
     fragen
    0.71
     zrozum
    0.71
     summarize
    0.69
     kategor
    0.69
    summar
    0.68
     festgestellt
    0.68
     summaries
    0.67
     hinsichtlich
    0.67
     sentimiento
    0.66
    Act Density 0.536%

    No Known Activations