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

    Neuronpedia

    INDEX
    Explanations

    guest speakers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maka
    -0.08
     demás
    -0.08
    Tracker
    -0.07
    規
    -0.07
    Nd
    -0.07
    _zip
    -0.07
    _unicode
    -0.07
    ិប
    -0.07
     coherent
    -0.07
    ข
    -0.07
    POSITIVE LOGITS
     alumni
    0.10
     experts
    0.09
     alumn
    0.09
     engineers
    0.09
     veterans
    0.09
     Architects
    0.09
     architects
    0.09
     vendors
    0.09
     chefs
    0.09
     internships
    0.09
    Act Density 0.022%

    No Known Activations