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

    Neuronpedia

    INDEX
    Explanations

    reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buffy
    -0.07
    机身
    -0.07
     Święt
    -0.07
    فن
    -0.07
     yönet
    -0.07
     wallets
    -0.07
    릏
    -0.06
     wary
    -0.06
     gone
    -0.06
     advocating
    -0.06
    POSITIVE LOGITS
     endforeach
    0.08
     Brussels
    0.07
     chac
    0.07
     cał
    0.07
    (length
    0.07
     remember
    0.07
    /frame
    0.07
    _numbers
    0.07
     rec
    0.07
    емых
    0.07
    Act Density 0.012%

    No Known Activations