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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    운
    -0.07
    onte
    -0.07
     vests
    -0.07
    -fired
    -0.07
    	org
    -0.07
    .lst
    -0.07
     hic
    -0.07
    ulaire
    -0.07
    _triggered
    -0.06
    瓮
    -0.06
    POSITIVE LOGITS
     지
    0.07
    .time
    0.06
     Cross
    0.06
    _RIGHT
    0.06
    Paragraph
    0.06
    Bi
    0.06
     Publishing
    0.06
     Cub
    0.06
     מדובר
    0.06
     Cruise
    0.06
    Act Density 0.113%

    No Known Activations