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

    Neuronpedia

    INDEX
    Explanations

    lists of options or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comprising
    0.40
     *
    0.38
     (*
    0.37
     comprises
    0.35
     /*
    0.34
     الرئيسية
    0.34
    )*
    0.33
     conforms
    0.33
     *$
    0.33
    ()*
    0.32
    POSITIVE LOGITS
     "...
    0.50
    '...
    0.48
    "...
    0.42
     ?></
    0.41
    ')))
    0.40
    $...
    0.40
    ...')
    0.39
    ...?
    0.38
    '?
    0.37
     '))
    0.37
    Act Density 0.114%

    No Known Activations