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

    Neuronpedia

    INDEX
    Explanations

    problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ern
    -0.07
    	con
    -0.07
     são
    -0.07
    	f
    -0.06
    .$
    -0.06
     RU
    -0.06
     consectetur
    -0.06
    (function
    -0.06
    ような
    -0.06
    	spec
    -0.06
    POSITIVE LOGITS
     syncing
    0.07
     Ved
    0.06
     carriage
    0.06
    inter
    0.06
    utch
    0.06
     Graphics
    0.06
    价值
    0.06
     अ
    0.06
     cheers
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.003%

    No Known Activations