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

    Neuronpedia

    INDEX
    Explanations

    Academic publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     могут
    -0.07
     Thy
    -0.07
    <th
    -0.07
     будет
    -0.06
    _the
    -0.06
     Swiss
    -0.06
     rằng
    -0.06
     elseif
    -0.06
     endif
    -0.06
     может
    -0.06
    POSITIVE LOGITS
     SPEC
    0.07
    กระ
    0.07
     Diameter
    0.07
     mileage
    0.07
    ()")↵
    0.06
     portrays
    0.06
     점
    0.06
     THANK
    0.06
    _Category
    0.06
     Cabinet
    0.06
    Act Density 0.004%

    No Known Activations