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

    Neuronpedia

    INDEX
    Explanations

    years old

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Derived
    0.53
    derived
    0.49
     Larger
    0.49
     propuesta
    0.48
     derived
    0.48
     ተጨማሪ
    0.47
     Derived
    0.47
     pariatur
    0.46
    jük
    0.46
     raíz
    0.46
    POSITIVE LOGITS
     old
    3.20
    old
    2.78
    Old
    2.69
     olds
    2.67
    老
    2.48
     Old
    2.47
     OLD
    2.38
    OLD
    2.28
    olds
    2.16
     vecchia
    2.06
    Act Density 0.067%

    No Known Activations