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

    Neuronpedia

    INDEX
    Explanations

    online orders and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parsed
    -0.08
     beginner
    -0.06
     Binder
    -0.06
    HANDLE
    -0.06
    lernen
    -0.06
     floor
    -0.06
     paypal
    -0.06
    _*
    -0.06
    adius
    -0.06
     Berlin
    -0.06
    POSITIVE LOGITS
    	source
    0.07
     Agricult
    0.07
    انون
    0.06
     ("/
    0.06
    )),↵
    0.06
    @class
    0.06
     �
    0.06
    (Error
    0.06
    clidean
    0.06
    ัดส
    0.06
    Act Density 0.015%

    No Known Activations