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

    Neuronpedia

    INDEX
    Explanations

    economic inflation and evolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     област
    0.46
    Actions
    0.40
    transit
    0.39
    ınca
    0.39
     Transit
    0.39
     zás
    0.38
     Actions
    0.38
     transit
    0.38
     시민
    0.38
    Action
    0.37
    POSITIVE LOGITS
     Behavior
    0.51
     behavior
    0.47
    behavior
    0.43
     variation
    0.41
    perception
    0.41
    調
    0.41
     evolution
    0.40
     pulver
    0.40
     percep
    0.40
     benchmark
    0.40
    Act Density 0.007%

    No Known Activations