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

    Neuronpedia

    INDEX
    Explanations

    tem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     improves
    -0.07
    FlatButton
    -0.07
     Swimming
    -0.07
     збільш
    -0.06
     LEVEL
    -0.06
    	  ↵
    -0.06
    สะ
    -0.06
    sample
    -0.06
     emotionally
    -0.06
    urette
    -0.06
    POSITIVE LOGITS
     Mahm
    0.07
    ftp
    0.07
     솔
    0.07
    _NAV
    0.06
     UIAlertAction
    0.06
    Ά
    0.06
     Prosec
    0.06
     �
    0.06
     Fraud
    0.06
    _template
    0.06
    Act Density 0.006%

    No Known Activations