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

    Neuronpedia

    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    иплом
    -0.08
     lei
    -0.07
    の方
    -0.07
    	debug
    -0.06
     DBHelper
    -0.06
    _TI
    -0.06
     باد
    -0.06
    ύν
    -0.06
     Hoe
    -0.06
    uges
    -0.06
    POSITIVE LOGITS
    ]")↵
    0.07
     населення
    0.06
     averaged
    0.06
     Maximum
    0.06
     deserving
    0.06
     maximum
    0.06
    )')↵
    0.06
     uniformly
    0.06
     SAFE
    0.06
    beth
    0.06
    Act Density 0.013%

    No Known Activations