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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tree
    -0.07
     vant
    -0.07
     seab
    -0.06
    ści
    -0.06
     Scot
    -0.06
    วโม
    -0.06
    commands
    -0.06
     UTF
    -0.06
     datastore
    -0.06
    .EventHandler
    -0.06
    POSITIVE LOGITS
     첨부파일
    0.08
    ISTICS
    0.07
    ões
    0.07
     achieves
    0.07
    omentum
    0.07
    кав
    0.06
     Annual
    0.06
    ebiliriz
    0.06
     interceptions
    0.06
    %%%%%%%%%%%%%%%%
    0.06
    Act Density 0.049%

    No Known Activations