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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    를
    -0.07
     Bew
    -0.06
    을
    -0.06
    .getFile
    -0.06
    드립니다
    -0.06
    Fear
    -0.06
     visto
    -0.06
    .Obj
    -0.06
     Prostit
    -0.06
    .center
    -0.06
    POSITIVE LOGITS
     RE
    0.08
    average
    0.07
    setScale
    0.07
    Heavy
    0.07
     مرحله
    0.07
     preached
    0.07
     heir
    0.07
    CRC
    0.06
     ortalama
    0.06
     رج
    0.06
    Act Density 0.020%

    No Known Activations