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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USD
    -0.07
    fatal
    -0.06
    graph
    -0.06
    ену
    -0.06
     female
    -0.06
    orners
    -0.06
     currencies
    -0.06
     ตร
    -0.06
    ++
    -0.06
    tp
    -0.06
    POSITIVE LOGITS
     redo
    0.07
    Bạn
    0.06
     mdb
    0.06
    sizeof
    0.06
     profound
    0.06
    ={({
    0.06
    prd
    0.06
    inject
    0.06
     Initialize
    0.06
    "He
    0.06
    Act Density 0.036%

    No Known Activations