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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	md
    -0.08
    unifu
    -0.08
    ragen
    -0.07
    .primary
    -0.07
     Nose
    -0.06
     Aux
    -0.06
    .Factory
    -0.06
     sonst
    -0.06
    μαι
    -0.06
    DESC
    -0.06
    POSITIVE LOGITS
    (AP
    0.06
     lacking
    0.06
    农业
    0.06
    ]]>
    0.06
    UCCEEDED
    0.06
     게시판
    0.06
    SystemService
    0.06
    斷
    0.06
    ющих
    0.06
    .persist
    0.05
    Act Density 0.029%

    No Known Activations