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

    Neuronpedia

    INDEX
    Explanations

    About the author

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نور
    -0.08
    ims
    -0.07
    standing
    -0.06
     Sp
    -0.06
    україн
    -0.06
     Kur
    -0.06
    调整
    -0.06
    _For
    -0.06
     winding
    -0.06
    trimmed
    -0.06
    POSITIVE LOGITS
     เก
    0.07
     dorsal
    0.07
    him
    0.06
     complied
    0.06
     diğer
    0.06
    起
    0.06
     skate
    0.06
    .proto
    0.06
     ра
    0.06
    (express
    0.06
    Act Density 0.041%

    No Known Activations