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

    Neuronpedia

    INDEX
    Explanations

    Developer tools

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reservoir
    -0.07
    orpor
    -0.07
    	count
    -0.07
     Libraries
    -0.07
     النق
    -0.07
    	R
    -0.07
    eka
    -0.07
    .setTime
    -0.06
     solids
    -0.06
     rats
    -0.06
    POSITIVE LOGITS
     sẵ
    0.07
    绐
    0.07
    ʣ
    0.07
    𐭍
    0.07
     bedeut
    0.06
    <input
    0.06
    ชำ
    0.06
    .fontSize
    0.06
    公里
    0.06
    剀
    0.06
    Act Density 0.002%

    No Known Activations