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

    Neuronpedia

    INDEX
    Explanations

    nested square roots, variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *↵↵
    -0.08
     leaks
    -0.08
    netz
    -0.07
    IHE
    -0.07
     ની
    -0.07
     Heng
    -0.07
     proposes
    -0.07
     .↵↵
    -0.07
     Hitch
    -0.07
     мех
    -0.07
    POSITIVE LOGITS
     repeatedly
    0.09
    越来越
    0.08
    □□□□□□□□□□□□□□□□
    0.08
    ервых
    0.08
    առ
    0.08
     voit
    0.08
     recursively
    0.07
    azos
    0.07
    按照
    0.07
     understandable
    0.07
    Act Density 0.015%

    No Known Activations