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

    Neuronpedia

    INDEX
    Explanations

    internal followed by specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    外
    0.54
     Outside
    0.54
    の外
    0.52
    outside
    0.51
    Outside
    0.49
    户外
    0.48
     বাইরে
    0.47
     外
    0.47
     Außen
    0.47
     outside
    0.46
    POSITIVE LOGITS
     internal
    1.33
     Internal
    1.22
     interne
    1.20
     internally
    1.18
    Internal
    1.14
     내부
    1.10
     INTERNAL
    1.08
    内部
    1.02
    internal
    1.02
    INTERNAL
    0.95
    Act Density 0.009%

    No Known Activations