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

    Neuronpedia

    INDEX
    Explanations

    code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    考证
    -0.07
    ران
    -0.07
    (Class
    -0.07
    써
    -0.07
     revisit
    -0.07
    解释
    -0.07
     wybrać
    -0.07
    ｻ
    -0.07
    	dx
    -0.07
     gather
    -0.07
    POSITIVE LOGITS
    .V
    0.09
     producers
    0.07
     escalation
    0.07
    ]];↵↵
    0.07
    乌
    0.07
    _daily
    0.07
     monoc
    0.07
    ИН
    0.07
     LIB
    0.07
     repercussions
    0.07
    Act Density 0.001%

    No Known Activations