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

    Neuronpedia

    INDEX
    Explanations

    Maven pom.xml files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingreso
    0.38
     rurales
    0.37
     Sal
    0.36
     amenaza
    0.36
     Internacional
    0.36
     農
    0.36
     Continent
    0.35
     الذين
    0.35
    قان
    0.35
     Mica
    0.34
    POSITIVE LOGITS
     POM
    0.48
    हट
    0.46
    POM
    0.43
    Pom
    0.39
    ientras
    0.39
     ouders
    0.39
    ImageType
    0.39
     pom
    0.38
    家长
    0.38
    arita
    0.38
    Act Density 0.000%

    No Known Activations