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

    Neuronpedia

    INDEX
    Explanations

    AWS code headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    νοι
    -0.07
     침
    -0.06
     sö
    -0.06
    _viewer
    -0.06
    ritch
    -0.06
     düşün
    -0.06
    knowledge
    -0.06
     tor
    -0.06
    bole
    -0.06
    ################
    -0.06
    POSITIVE LOGITS
     sentenced
    0.07
    _rx
    0.07
    값
    0.06
    )...
    0.06
    Phil
    0.06
     можно
    0.06
     waren
    0.06
    ตำบล
    0.06
     inmate
    0.06
     localVar
    0.06
    Act Density 0.005%

    No Known Activations