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

    Neuronpedia

    INDEX
    Explanations

    conduit type or armor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    並
    0.40
     appliance
    0.40
     levers
    0.37
     hilltop
    0.36
     snappy
    0.36
    擎
    0.36
     fault
    0.36
     beep
    0.35
    ダンス
    0.35
     экзем
    0.35
    POSITIVE LOGITS
     জাল
    0.48
     চাওয়া
    0.41
    יה
    0.40
     실험
    0.40
     +\
    0.39
    цами
    0.39
     cuộc
    0.37
     cajas
    0.37
    asten
    0.36
    četně
    0.36
    Act Density 0.000%

    No Known Activations