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

    Neuronpedia

    INDEX
    Explanations

    and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pennsylvania
    0.45
     Catholics
    0.45
     पश्चिम
    0.44
     КП
    0.44
     rural
    0.43
     katol
    0.43
    ပိုင်း
    0.41
     منشور
    0.41
     டே
    0.41
    儆
    0.41
    POSITIVE LOGITS
    It
    0.47
    ení
    0.46
    rett
    0.44
    物理
    0.44
    ϝ
    0.43
     stateMutability
    0.43
    Ý
    0.42
    Oui
    0.42
    StatusInternal
    0.41
    EM
    0.41
    Act Density 0.049%

    No Known Activations