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

    Neuronpedia

    INDEX
    Explanations

    guidelines in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appliance
    0.43
     Integrity
    0.41
     আচ্ছা
    0.41
     သင်
    0.41
     mathematician
    0.40
    উক
    0.39
     beam
    0.39
     dude
    0.39
     transparent
    0.38
     aslında
    0.37
    POSITIVE LOGITS
    buri
    0.51
     چندین
    0.51
     soutenir
    0.48
    薜
    0.48
     எனும்
    0.46
     защото
    0.46
    ოვ
    0.45
     आणि
    0.45
    埼
    0.45
     گوگل
    0.45
    Act Density 0.092%

    No Known Activations