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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mpi
    -0.07
    privacy
    -0.06
    earn
    -0.06
     globally
    -0.06
     вул
    -0.06
     nutrients
    -0.06
     亚洲
    -0.06
     ogr
    -0.06
     nostalgia
    -0.06
     全
    -0.06
    POSITIVE LOGITS
     underscore
    0.07
    	Dictionary
    0.07
     Zu
    0.07
    .dy
    0.07
    sel
    0.07
    sumer
    0.06
    ừa
    0.06
    -c
    0.06
    _phy
    0.06
    بیر
    0.06
    Act Density 0.001%

    No Known Activations