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

    Neuronpedia

    INDEX
    Explanations

    loading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lle
    -0.07
    olesterol
    -0.07
     haber
    -0.07
    Merge
    -0.06
     signal
    -0.06
    <Book
    -0.06
    iator
    -0.06
    umont
    -0.06
     Blend
    -0.06
     jusqu
    -0.06
    POSITIVE LOGITS
     Indianapolis
    0.07
    Appear
    0.07
    ้ง
    0.06
     jam
    0.06
     않았
    0.06
    UPI
    0.06
     следует
    0.06
    “그
    0.06
    iyi
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations