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

    Neuronpedia

    INDEX
    Explanations

    years in categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    วร
    -0.07
     =='
    -0.07
     퍼
    -0.06
    悠
    -0.06
     Yes
    -0.06
    대회
    -0.06
    ForRow
    -0.06
     �
    -0.06
    stories
    -0.06
     Hick
    -0.06
    POSITIVE LOGITS
     appellate
    0.07
     отнош
    0.07
    usahaan
    0.06
     influence
    0.06
     specializes
    0.06
     ara
    0.06
     varieties
    0.06
     means
    0.06
     asympt
    0.06
     sdl
    0.06
    Act Density 0.002%

    No Known Activations