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

    Neuronpedia

    INDEX
    Explanations

    formulae and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الطيب
    0.43
     चारों
    0.43
     జ
    0.41
     друзья
    0.41
     Editor
    0.41
    টন
    0.41
    न्यास
    0.40
    國際
    0.40
     Tony
    0.39
    сіб
    0.39
    POSITIVE LOGITS
     caloric
    0.47
     funzione
    0.46
     funcionar
    0.45
     vit
    0.43
     cube
    0.42
     Linie
    0.42
     odgov
    0.42
     ço
    0.41
     funcione
    0.41
     footage
    0.40
    Act Density 0.002%

    No Known Activations