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

    Neuronpedia

    INDEX
    Explanations

    the followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oloj
    0.39
    시에
    0.39
    bye
    0.38
    unn
    0.38
    پا
    0.38
    Decrease
    0.38
    Flare
    0.38
    SIS
    0.37
    व्यापी
    0.37
    Bye
    0.37
    POSITIVE LOGITS
     motionProxy
    0.38
    ക്‌
    0.38
    玄関
    0.37
     কিংবা
    0.37
    घन
    0.37
     drags
    0.37
     própria
    0.36
     ओवर
    0.35
    竣
    0.35
     próprios
    0.35
    Act Density 0.000%

    No Known Activations