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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laguna
    -0.06
     암
    -0.06
     plaintiff
    -0.06
     NavController
    -0.06
     hauling
    -0.06
    Dao
    -0.06
    __$
    -0.06
     quietly
    -0.06
    очку
    -0.06
     prev
    -0.05
    POSITIVE LOGITS
     excessive
    0.07
    zs
    0.07
     پزشکی
    0.07
     unstable
    0.07
    ful
    0.06
    ARP
    0.06
    ثیر
    0.06
     versions
    0.06
    abal
    0.06
    userData
    0.06
    Act Density 0.002%

    No Known Activations