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

    Neuronpedia

    INDEX
    Explanations

    causing serious harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Say
    0.40
     Бога
    0.39
     Tulsa
    0.38
     তথা
    0.37
     té
    0.36
    ."-
    0.36
     greeting
    0.35
    ജി
    0.35
     சொல்
    0.35
     mét
    0.35
    POSITIVE LOGITS
    continue
    0.38
    ggac
    0.38
    äs
    0.37
    鏝
    0.37
    bewegung
    0.37
    iec
    0.35
    Continuing
    0.35
    skim
    0.35
    bypass
    0.35
    Excluded
    0.35
    Act Density 0.000%

    No Known Activations