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

    Neuronpedia

    INDEX
    Explanations

    Repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amenities
    -0.08
    ंब
    -0.07
    unittest
    -0.06
     além
    -0.06
    _cut
    -0.06
     зап
    -0.06
     Bits
    -0.06
     qu
    -0.06
    �
    -0.06
    γγ
    -0.06
    POSITIVE LOGITS
    keterangan
    0.07
     prostituerade
    0.07
    outs
    0.07
    zeitig
    0.06
     bậc
    0.06
    -context
    0.06
     постоянно
    0.06
    letcher
    0.06
     القد
    0.06
     prostate
    0.06
    Act Density 0.015%

    No Known Activations