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

    Neuronpedia

    INDEX
    Explanations

    curly brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SK
    -0.07
     Latter
    -0.07
    dependence
    -0.06
     WPARAM
    -0.06
    outline
    -0.06
    饮
    -0.06
    connections
    -0.06
     Fundamental
    -0.06
    Translate
    -0.06
    Johnson
    -0.06
    POSITIVE LOGITS
     zij
    0.06
    \Category
    0.06
    uclear
    0.06
     бла
    0.06
     disturbing
    0.06
     Wow
    0.06
    oving
    0.06
     empresa
    0.05
    ()]↵↵
    0.05
     कथ
    0.05
    Act Density 0.020%

    No Known Activations