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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البن
    -0.07
    חופ
    -0.07
     Flu
    -0.07
     Lightning
    -0.07
    LBL
    -0.07
     sails
    -0.07
    Ě
    -0.07
    Fe
    -0.06
     discovers
    -0.06
    ⇧
    -0.06
    POSITIVE LOGITS
    .directory
    0.08
    תרבות
    0.08
        
↵    
↵
    0.07
     quarterly
    0.07
    ların
    0.07
    -capital
    0.07
    	area
    0.07
    &(
    0.07
     disturbed
    0.07
     ,(
    0.07
    Act Density 0.014%

    No Known Activations