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

    Neuronpedia

    INDEX
    Explanations

    the, my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дей
    -0.08
    todos
    -0.08
     приложения
    -0.08
     Frm
    -0.07
     vars
    -0.07
     Frankenstein
    -0.07
     Fy
    -0.07
     aspiration
    -0.07
    stum
    -0.07
    /of
    -0.07
    POSITIVE LOGITS
     postpartum
    0.09
    medi
    0.08
     aposent
    0.08
     enact
    0.07
     سوى
    0.07
     Canterbury
    0.07
     Tan
    0.07
     уволь
    0.07
     monarchy
    0.07
    ാന്ത
    0.07
    Act Density 0.026%

    No Known Activations