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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tah
    -0.07
    enkins
    -0.07
    毹
    -0.07
    ,X
    -0.07
    -0.06
    .TypeOf
    -0.06
     Fig
    -0.06
     unsett
    -0.06
    的具体
    -0.06
     ant
    -0.06
    POSITIVE LOGITS
    杙
    0.07
    bru
    0.07
     agréable
    0.07
    אוט
    0.07
    uebas
    0.07
     Voters
    0.07
    ointments
    0.07
    Production
    0.07
    .page
    0.07
    lightly
    0.07
    Act Density 0.208%

    No Known Activations