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

    Neuronpedia

    INDEX
    Explanations

    igi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jones
    -0.07
    Hand
    -0.06
    CDATA
    -0.06
     aerial
    -0.06
    'I
    -0.06
    方
    -0.06
    realDonaldTrump
    -0.06
    ROC
    -0.06
    'order
    -0.06
     badly
    -0.06
    POSITIVE LOGITS
     různých
    0.07
     устрой
    0.06
    larına
    0.06
    '){
↵
    0.06
    */↵↵
    0.06
     избав
    0.06
     ({↵
    0.06
     =>↵
    0.06
    амп
    0.06
     StringField
    0.06
    Act Density 0.032%

    No Known Activations