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

    Neuronpedia

    INDEX
    Explanations

    lists of pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :"))
    0.60
    :</
    0.50
    譬
    0.46
     경우에는
    0.45
     或者
    0.45
    比如说
    0.45
    :")
    0.44
    कांनी
    0.44
     或
    0.43
    :");
    0.43
    POSITIVE LOGITS
    ;
    0.88
    !,
    0.82
    ?,
    0.78
    ،
    0.65
    ؛
    0.65
     $,
    0.63
    ；
    0.63
    °,
    0.62
    +,
    0.62
     ?,
    0.61
    Act Density 0.173%

    No Known Activations