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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itor
    -0.07
    oma
    -0.07
     Mad
    -0.06
    들도
    -0.06
     ISC
    -0.06
     trapping
    -0.06
     MAD
    -0.06
    Las
    -0.06
     suicide
    -0.06
    BLOCK
    -0.06
    POSITIVE LOGITS
    군
    0.07
     konz
    0.07
     slov
    0.07
     gst
    0.06
     замов
    0.06
    ्वत
    0.06
    施工
    0.06
     zkušen
    0.06
     Sark
    0.06
     lastName
    0.06
    Act Density 0.025%

    No Known Activations