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
    Orders
    -0.06
    	↵	↵↵
    -0.06
     світу
    -0.06
     delivering
    -0.06
    uche
    -0.06
    straints
    -0.06
    EDIUM
    -0.06
     Descriptor
    -0.06
    TOTAL
    -0.06
    .prob
    -0.06
    POSITIVE LOGITS
    :E
    0.07
     있고
    0.07
     JNI
    0.06
    .setAction
    0.06
    럼
    0.06
     removes
    0.06
     şeyler
    0.06
    ;p
    0.06
     Convention
    0.06
     hòa
    0.06
    Act Density 0.001%

    No Known Activations