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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uranium
    -0.07
     ofrece
    -0.07
     slider
    -0.07
     جي
    -0.06
     输入
    -0.06
     выступ
    -0.06
     سری
    -0.06
    ыш
    -0.06
     있는
    -0.06
     بیمه
    -0.06
    POSITIVE LOGITS
     inferior
    0.06
     Machinery
    0.06
    atching
    0.06
    .web
    0.06
     romant
    0.06
     професій
    0.06
     Firm
    0.06
     commas
    0.06
     Bağ
    0.06
     instantaneous
    0.06
    Act Density 0.052%

    No Known Activations