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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aid
    -0.07
    aggi
    -0.07
     />,↵
    -0.06
     başladı
    -0.06
    sanız
    -0.06
    y
    -0.06
    ocos
    -0.06
    G
    -0.06
     Journey
    -0.06
    (employee
    -0.06
    POSITIVE LOGITS
     Originally
    0.07
    ibre
    0.07
     Deleting
    0.07
    Ptr
    0.06
     θα
    0.06
    ……」↵↵
    0.06
    imeters
    0.06
     DELETE
    0.06
    .MapFrom
    0.06
    CADE
    0.06
    Act Density 0.056%

    No Known Activations