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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cyc
    -0.08
    Dan
    -0.07
     रस
    -0.07
     hồi
    -0.07
     Dan
    -0.06
    Pan
    -0.06
     caves
    -0.06
     troops
    -0.06
    193
    -0.06
     archae
    -0.06
    POSITIVE LOGITS
     washington
    0.08
    لس
    0.06
    .Promise
    0.06
     :
    0.06
    (skill
    0.06
    ROLE
    0.06
     erv
    0.06
    IE
    0.06
    ่อย
    0.06
    -if
    0.06
    Act Density 0.024%

    No Known Activations