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
    -location
    -0.06
     Viewer
    -0.06
    -menu
    -0.06
     paw
    -0.06
     experts
    -0.06
    ra
    -0.06
     cameo
    -0.06
     _{
    -0.06
     الأرض
    -0.06
    uae
    -0.05
    POSITIVE LOGITS
     recuper
    0.07
     toc
    0.07
     tantra
    0.07
     yasak
    0.07
     sanctioned
    0.07
    _SCRIPT
    0.07
    좋
    0.07
    _PRINT
    0.06
    ROT
    0.06
     câ
    0.06
    Act Density 0.058%

    No Known Activations