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

    Neuronpedia

    INDEX
    Explanations

    Math expressions and reductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    दै
    -0.07
    ्
    -0.07
    ದೆ
    -0.07
    觉得
    -0.07
    -0.07
    .once
    -0.07
    ద్�
    -0.07
    venido
    -0.07
    색
    -0.07
    દદ
    -0.07
    POSITIVE LOGITS
     gcd
    0.09
    Syl
    0.09
     حفاظت
    0.08
     chịu
    0.08
    )=
    0.07
     خش
    0.07
     accidentes
    0.07
    }))
    0.07
     integers
    0.07
     קש
    0.07
    Act Density 0.029%
    No Known Activations