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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Answers
    -0.07
     Insurance
    -0.06
    _Name
    -0.06
     invading
    -0.06
     рук
    -0.06
     Bose
    -0.06
     Hàng
    -0.06
    _estimate
    -0.06
    ادم
    -0.06
    腹
    -0.06
    POSITIVE LOGITS
    erc
    0.07
    0.07
       ↵↵
    0.07
    tab
    0.06
     bool
    0.06
    models
    0.06
    ivery
    0.06
    	my
    0.06
     getUser
    0.06
    0.06
    Act Density 0.000%

    No Known Activations