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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tối
    -0.07
     least
    -0.07
     bunk
    -0.06
     uncert
    -0.06
    	ev
    -0.06
    俙
    -0.06
    健全
    -0.06
    .Branch
    -0.06
     stanza
    -0.06
    Anything
    -0.06
    POSITIVE LOGITS
    ięć
    0.07
     marginLeft
    0.07
     méd
    0.07
    bilt
    0.07
     ██
    0.07
     Lakers
    0.07
    SELECT
    0.07
     Gregory
    0.07
     dönem
    0.07
    ים
    0.07
    Act Density 0.002%

    No Known Activations