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

    Neuronpedia

    INDEX
    Explanations

    what comes next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actual
    0.44
    劣化
    0.44
     நமக்கு
    0.42
     largely
    0.41
     eigent
    0.40
     నాకు
    0.40
    Actual
    0.40
     corollary
    0.40
     convincing
    0.39
     propagand
    0.39
    POSITIVE LOGITS
     "...
    0.71
     "`
    0.67
     “…
    0.66
     "[
    0.66
     "'
    0.65
     "..
    0.64
     “‘
    0.63
     “[
    0.61
     pihaknya
    0.61
     unspecified
    0.60
    Act Density 0.013%

    No Known Activations