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

    Neuronpedia

    INDEX
    Explanations

    Colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     efficiencies
    -0.06
     Bundy
    -0.06
     inconsistent
    -0.06
    بير
    -0.06
     Bars
    -0.06
     currentUser
    -0.06
    maf
    -0.06
     estilo
    -0.06
    аша
    -0.06
     reasons
    -0.06
    POSITIVE LOGITS
    alore
    0.07
     pageCount
    0.07
    ء
    0.06
     adulte
    0.06
     */↵↵↵↵
    0.06
    stride
    0.06
     mere
    0.06
    .Threading
    0.06
    ']],
    0.06
     realtime
    0.06
    Act Density 0.010%

    No Known Activations