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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    partment
    -0.07
     detox
    -0.07
     placing
    -0.07
     outcomes
    -0.06
     squeezing
    -0.06
    .tree
    -0.06
     planting
    -0.06
    ุญ
    -0.06
    -deals
    -0.06
    Footer
    -0.06
    POSITIVE LOGITS
    	HANDLE
    0.07
    (ld
    0.07
     neod
    0.06
     olay
    0.06
     İnsan
    0.06
     yapıyor
    0.06
     mp
    0.06
     podob
    0.06
    ाएग
    0.06
    xFFFF
    0.06
    Act Density 0.017%

    No Known Activations