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

    Neuronpedia

    INDEX
    Explanations

    Acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conquered
    -0.06
     Reb
    -0.06
     AC
    -0.06
    planation
    -0.06
     COP
    -0.06
    чень
    -0.06
     Implemented
    -0.06
     Jac
    -0.06
     Anc
    -0.05
     Buildings
    -0.05
    POSITIVE LOGITS
    …
    0.07
     fronts
    0.07
     faiz
    0.07
     awaits
    0.07
     reins
    0.07
     hungry
    0.07
     strcpy
    0.07
    imler
    0.07
    utility
    0.07
     AsyncStorage
    0.06
    Act Density 0.002%

    No Known Activations