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

    Neuronpedia

    INDEX
    Explanations

    nuance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ઉપરાંત
    -0.09
     respectable
    -0.08
     excellent
    -0.08
     Bett
    -0.08
     virtues
    -0.08
    din
    -0.08
     Kawasaki
    -0.07
     empowers
    -0.07
    Detected
    -0.07
     koliko
    -0.07
    POSITIVE LOGITS
     बना
    0.09
     जा
    0.08
     Alam
    0.08
     PW
    0.08
     Hom
    0.07
     dwell
    0.07
     EH
    0.07
     जाये
    0.07
    ↵	
↵
    0.07
    _pw
    0.07
    Act Density 0.048%

    No Known Activations