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

    Neuronpedia

    INDEX
    Explanations

    posted

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assertion
    -0.06
    rapper
    -0.06
     recruitment
    -0.06
     EQ
    -0.06
     gz
    -0.06
     —↵
    -0.06
    uracy
    -0.06
    )?.
    -0.06
     '*
    -0.06
     LoginPage
    -0.06
    POSITIVE LOGITS
    (stypy
    0.07
    WhiteSpace
    0.07
     Guinea
    0.07
    Pear
    0.07
    (inertia
    0.07
     يع
    0.06
     gracias
    0.06
    	vertices
    0.06
     Sil
    0.06
     assim
    0.06
    Act Density 0.002%

    No Known Activations