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

    Neuronpedia

    INDEX
    Explanations

    tool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ièrement
    -0.07
     represented
    -0.06
     landscapes
    -0.06
     houses
    -0.06
     deleted
    -0.06
    endor
    -0.06
     friction
    -0.06
     railways
    -0.06
    '↵↵↵↵
    -0.06
    lines
    -0.06
    POSITIVE LOGITS
    방법
    0.07
    治疗
    0.06
    .job
    0.06
     poj
    0.06
    ,w
    0.06
    0.06
    	row
    0.06
    �
    0.06
     SEP
    0.06
    -BEGIN
    0.06
    Act Density 0.013%

    No Known Activations