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

    Neuronpedia

    INDEX
    Explanations

    often involve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bill
    0.38
     Sylvain
    0.37
    CV
    0.35
     Syndrome
    0.34
     Nxc
    0.34
     Burning
    0.34
     Scanning
    0.33
    ழு
    0.33
    tt
    0.33
     Mu
    0.33
    POSITIVE LOGITS
     görüntü
    0.43
    ancı
    0.43
     окончания
    0.41
     sete
    0.41
     incessantly
    0.41
    াপাশি
    0.40
     stretches
    0.39
    ವಹ
    0.39
    mlich
    0.39
     უნდა
    0.38
    Act Density 0.000%

    No Known Activations