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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spe
    -0.08
     speaks
    -0.07
    ้าง
    -0.07
    มาก
    -0.07
    FieldType
    -0.07
    不断
    -0.07
    표
    -0.07
    𬀪
    -0.07
    worthy
    -0.07
    接管
    -0.07
    POSITIVE LOGITS
     distressed
    0.07
    ITIONAL
    0.07
    	layer
    0.07
    ollapsed
    0.07
     Greenwich
    0.07
     Low
    0.07
     compressed
    0.06
     manufactured
    0.06
    ACCESS
    0.06
     progressed
    0.06
    Act Density 0.000%

    No Known Activations