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

    Neuronpedia

    INDEX
    Explanations

    know/understand

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ให้กับ
    0.82
     varit
    0.71
     hasn
    0.70
    されていない
    0.68
     haven
    0.68
    Haven
    0.67
    働
    0.66
     dimiliki
    0.65
     berupa
    0.65
    偏
    0.65
    POSITIVE LOGITS
     knows
    1.40
     knew
    1.32
     understand
    1.29
     understands
    1.28
     know
    1.24
     knowing
    1.24
     Know
    1.16
    Learn
    1.16
     learn
    1.16
    understand
    1.16
    Act Density 0.296%

    No Known Activations