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

    Neuronpedia

    INDEX
    Explanations

    Dick Smith Fun Way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डेड
    0.38
    Spy
    0.35
    trek
    0.35
    enter
    0.34
    opic
    0.33
     Dyn
    0.33
     sauté
    0.33
    ുണ്ട
    0.33
     Gl
    0.32
     Rope
    0.32
    POSITIVE LOGITS
     맥
    0.48
     진
    0.43
    zechoslovakia
    0.39
    قاء
    0.39
     germany
    0.39
    phrase
    0.38
    Phrase
    0.38
    naf
    0.38
     ż
    0.37
     inklusive
    0.37
    Act Density 0.001%

    No Known Activations