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

    Neuronpedia

    INDEX
    Explanations

    based on that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     läh
    0.44
    áš
    0.43
     आपकी
    0.42
    런
    0.42
     jūs
    0.42
    你在
    0.41
    伦敦
    0.41
    jols
    0.41
    ایک
    0.41
     bạn
    0.40
    POSITIVE LOGITS
     intrinsically
    0.41
    ರುತ್ತದೆ
    0.41
    StripMenuItem
    0.40
     inflated
    0.39
     infused
    0.38
    Semaphore
    0.37
    configured
    0.37
     textured
    0.36
     increases
    0.36
     configured
    0.36
    Act Density 0.001%

    No Known Activations