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

    Neuronpedia

    INDEX
    Explanations

    long story

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्र
    -0.07
     이번
    -0.07
     masih
    -0.07
    belt
    -0.07
    	cur
    -0.06
    ові
    -0.06
     quot
    -0.06
     conveyor
    -0.06
     Dee
    -0.06
     embassy
    -0.06
    POSITIVE LOGITS
    awaiter
    0.06
     порядке
    0.06
     recommended
    0.06
    559
    0.06
     searching
    0.06
     tasked
    0.06
    �
    0.06
     کامل
    0.06
     μια
    0.06
     caution
    0.06
    Act Density 0.023%

    No Known Activations