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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )를
    -0.08
    िसस
    -0.08
     बदल
    -0.07
     erro
    -0.07
     guarantees
    -0.07
    te
    -0.07
     nucle
    -0.07
    =create
    -0.07
     cannot
    -0.07
     전체
    -0.07
    POSITIVE LOGITS
     among
    0.19
     Among
    0.16
    Among
    0.14
    among
    0.13
     amongst
    0.12
     среди
    0.09
    olumn
    0.08
    松
    0.07
     Серед
    0.07
    มห
    0.07
    Act Density 0.017%

    No Known Activations