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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    님의
    -0.07
     رشد
    -0.07
     پدر
    -0.06
     '&'
    -0.06
     owners
    -0.06
    photo
    -0.06
    ítulo
    -0.06
    rello
    -0.06
     krij
    -0.06
     Hero
    -0.06
    POSITIVE LOGITS
    	INT
    0.07
    ]
↵
    0.06
    643
    0.06
     non
    0.06
    -int
    0.06
    idel
    0.06
     rozhod
    0.06
     anzeigen
    0.06
     сама
    0.06
     =================
    0.06
    Act Density 0.011%

    No Known Activations