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

    Neuronpedia

    INDEX
    Explanations

    Shankara

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lay
    -0.07
    ян
    -0.06
    君
    -0.06
    -payment
    -0.06
    indered
    -0.06
     Öz
    -0.06
    ีต
    -0.06
    	tc
    -0.06
    .onView
    -0.06
     hockey
    -0.06
    POSITIVE LOGITS
    (statement
    0.07
     khung
    0.07
     şun
    0.06
     downside
    0.06
     вся
    0.06
    酸
    0.06
     csr
    0.06
     ins
    0.06
    spr
    0.06
    your
    0.06
    Act Density 0.000%

    No Known Activations