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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginning
    -0.07
    lant
    -0.06
    bara
    -0.06
     Branch
    -0.06
     Pune
    -0.06
     Austrian
    -0.06
    -this
    -0.06
     waive
    -0.06
    iculo
    -0.06
    นวย
    -0.06
    POSITIVE LOGITS
    %p
    0.06
     электр
    0.06
    效果
    0.06
    ویه
    0.06
     gelişim
    0.06
    Doctors
    0.06
    	LOG
    0.06
     사이트
    0.06
    	printf
    0.06
     LogLevel
    0.06
    Act Density 0.012%

    No Known Activations