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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    at
    -0.08
    “At
    -0.07
     parsing
    -0.07
    afc
    -0.07
    AT
    -0.07
    「我
    -0.07
    "At
    -0.07
     trained
    -0.07
    “What
    -0.07
    "What
    -0.07
    POSITIVE LOGITS
    ]$
    0.08
     wholes
    0.08
    .$
    0.07
    \)
    0.07
    ."]↵
    0.07
    )$
    0.07
     Poll
    0.07
    .FILES
    0.06
     pneum
    0.06
     BitmapFactory
    0.06
    Act Density 0.048%

    No Known Activations