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

    Neuronpedia

    INDEX
    Explanations

    number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     초
    -0.07
    ACEMENT
    -0.07
     darker
    -0.07
    iore
    -0.06
    	area
    -0.06
    олее
    -0.06
     оз
    -0.06
    (course
    -0.06
    acity
    -0.06
    UITableViewCell
    -0.06
    POSITIVE LOGITS
     kindly
    0.07
    แกรม
    0.07
     неб
    0.07
     šp
    0.06
    ?'
    0.06
     Japon
    0.06
     Cave
    0.06
    JE
    0.06
    -П
    0.06
     poprvé
    0.06
    Act Density 0.044%

    No Known Activations