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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ukraine
    -0.07
     succession
    -0.07
    Spain
    -0.06
     theaters
    -0.06
    Streaming
    -0.06
     дитини
    -0.06
     loan
    -0.06
    #from
    -0.06
     testimony
    -0.06
     currentIndex
    -0.06
    POSITIVE LOGITS
     elect
    0.07
    taş
    0.07
     collar
    0.07
     установ
    0.07
     PD
    0.07
    ông
    0.06
    -collar
    0.06
    arme
    0.06
    GPU
    0.06
     Power
    0.06
    Act Density 0.013%

    No Known Activations