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

    Neuronpedia

    INDEX
    Explanations

    regions and political divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nour
    0.42
     Angry
    0.39
     Doctrine
    0.37
     imaginary
    0.37
     Sentence
    0.37
     angry
    0.37
    Angry
    0.37
     Evangelical
    0.36
    ovenant
    0.35
    期待
    0.35
    POSITIVE LOGITS
     packages
    0.48
     caminos
    0.44
    ڕۆ
    0.42
     kits
    0.41
     fondos
    0.40
     quals
    0.40
     roadways
    0.40
    Fols
    0.39
    rizona
    0.39
     पैकेज
    0.39
    Act Density 0.000%

    No Known Activations