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

    Neuronpedia

    INDEX
    Explanations

    end of quote or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "(
    0.56
     "[
    0.54
     "'
    0.54
    "[
    0.53
     "\"
    0.51
     '[
    0.50
    !",
    0.50
    }.",
    0.48
    ".[
    0.48
    ","
    0.47
    POSITIVE LOGITS
    ?’”
    0.54
    ‌ای
    0.51
    Indeed
    0.48
    ?”
    0.47
    ’”
    0.47
    ,’”
    0.46
    ’.”
    0.46
    Pause
    0.46
    ?’
    0.45
     ‘
    0.45
    Act Density 0.008%

    No Known Activations