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

    Neuronpedia

    INDEX
    Explanations

    token expiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    城乡
    0.40
     ત્યારબાદ
    0.40
    emetery
    0.38
    বিত্র
    0.38
    strncpy
    0.38
     покупа
    0.35
    ettamente
    0.35
    Dead
    0.35
    صیٰ
    0.35
     nourishing
    0.34
    POSITIVE LOGITS
     relacionada
    0.45
     MC
    0.44
     MCD
    0.44
     relacionado
    0.44
     aprender
    0.43
     youtube
    0.43
     MCQ
    0.42
    ቀ
    0.42
     questões
    0.42
     refer
    0.41
    Act Density 0.000%

    No Known Activations