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

    Neuronpedia

    INDEX
    Explanations

    acting strangely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    δη
    0.41
     convolution
    0.39
    Transmit
    0.39
    inher
    0.38
    传
    0.38
    Convention
    0.38
     arguments
    0.37
    Arguments
    0.37
    观察
    0.37
    Mock
    0.36
    POSITIVE LOGITS
    ↥
    0.43
     ഹോ
    0.42
     Verfügung
    0.42
     Сара
    0.41
    aredo
    0.40
    alkeeper
    0.40
     Bohemia
    0.40
    畊
    0.40
     एपल
    0.40
     தொழில்நுட்ப
    0.39
    Act Density 0.001%

    No Known Activations