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

    Neuronpedia

    INDEX
    Explanations

    series and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    1.34
    :
    1.14
     on
    1.13
    ০০
    1.11
    ление
    1.07
     to
    1.04
    د
    1.04
    ğı
    1.02
     is
    1.00
    ン
    0.99
    POSITIVE LOGITS
    u
    1.01
    ફેદ
    0.97
    ின்
    0.96
     Zuf
    0.87
     Feuilles
    0.86
    கால
    0.86
     Володи
    0.86
    കൊണ്ട്
    0.85
     Фурга
    0.84
    Види
    0.84
    Act Density 0.064%

    No Known Activations