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

    Neuronpedia

    INDEX
    Explanations

    placenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +'\
    -0.07
     वन
    -0.07
    .Annotations
    -0.06
    Trad
    -0.06
     첫
    -0.06
     happy
    -0.06
     tuberculosis
    -0.06
     번
    -0.06
    Lots
    -0.06
    Fs
    -0.06
    POSITIVE LOGITS
     CENT
    0.07
     São
    0.06
    塞
    0.06
    contador
    0.06
    
    0.06
     Mississippi
    0.06
    กฎ
    0.06
     si
    0.06
    CD
    0.06
    jej
    0.06
    Act Density 0.335%

    No Known Activations