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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.59
     (
    0.55
    ↵
    0.52
     can
    0.48
    -
    0.43
    ↵↵
    0.43
      
    0.42
     /
    0.42
    can
    0.42
    (
    0.41
    POSITIVE LOGITS
    바일
    0.46
     ಸರ್ಕಾರದ
    0.46
    ৩৭
    0.45
     Ouvrard
    0.43
    ংকের
    0.42
     ನಾವು
    0.42
     morphisms
    0.42
     ټینس
    0.42
    睐
    0.42
    െല്ലാം
    0.42
    Act Density 0.023%

    No Known Activations