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

    Neuronpedia

    INDEX
    Explanations

    tokens followed by this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সেসব
    0.72
     ඒවා
    0.63
     அவற்றை
    0.62
     அவற்றில்
    0.62
     öyle
    0.60
     সেগুলো
    0.58
     esos
    0.55
     naquele
    0.54
    걔
    0.52
     dichas
    0.52
    POSITIVE LOGITS
     this
    3.83
     هذا
    3.83
    this
    3.47
     этого
    3.31
     этом
    3.25
     questo
    3.23
     This
    3.08
     цього
    3.05
    This
    3.00
     این
    2.98
    Act Density 1.602%

    No Known Activations