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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philippe
    -0.08
     typical
    -0.07
     php
    -0.07
     Craw
    -0.07
     classifiers
    -0.07
    央
    -0.07
    iyat
    -0.07
    umbling
    -0.07
    CSC
    -0.07
     Sergey
    -0.07
    POSITIVE LOGITS
    િકેટ
    0.09
     рассказ
    0.08
     Explain
    0.08
    Explain
    0.08
     erklär
    0.08
     સ
    0.07
     erklären
    0.07
     നൽകി
    0.07
     गोल
    0.07
     സ്
    0.07
    Act Density 0.113%

    No Known Activations