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

    Neuronpedia

    INDEX
    Explanations

    regions and their notable features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     need
    0.46
     weeds
    0.46
     puissent
    0.44
     require
    0.42
    uristic
    0.38
     REQUIRE
    0.38
    都需要
    0.38
     تحتاج
    0.38
     weed
    0.37
     potranno
    0.37
    POSITIVE LOGITS
     boasts
    0.95
     dominated
    0.84
     boasting
    0.83
     home
    0.80
     birthplace
    0.80
    home
    0.72
     boast
    0.72
     hogar
    0.71
     famosa
    0.68
     terkenal
    0.68
    Act Density 0.014%

    No Known Activations