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

    Neuronpedia

    INDEX
    Explanations

    places and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     경험
    0.52
     समेत
    0.51
    acariy
    0.49
     근무
    0.47
    ิม
    0.47
    𐰚
    0.46
    РО
    0.46
     영향
    0.46
    юр
    0.45
     esperienze
    0.45
    POSITIVE LOGITS
     F
    0.47
     length
    0.46
     body
    0.45
     void
    0.45
     device
    0.45
     whole
    0.44
     def
    0.43
     variable
    0.43
     r
    0.43
     set
    0.43
    Act Density 0.032%

    No Known Activations