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

    Neuronpedia

    INDEX
    Explanations

    Dr. Seuss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ثلاثة
    0.56
    COMP
    0.52
     гэ
    0.52
     Calcul
    0.50
    t
    0.50
     utilización
    0.50
     Get
    0.49
     destrucción
    0.49
     கால
    0.48
    장은
    0.48
    POSITIVE LOGITS
    ਕਾਰ
    0.58
     novelists
    0.52
     sleek
    0.50
    idavit
    0.50
    quefois
    0.49
    setLookAndFeel
    0.48
    pleClass
    0.48
    wright
    0.48
     segala
    0.47
    tavern
    0.47
    Act Density 0.000%

    No Known Activations