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

    Neuronpedia

    INDEX
    Explanations

    practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esos
    -0.06
     نوش
    -0.06
     Yeni
    -0.06
     cores
    -0.06
     ประเภท
    -0.06
    软件
    -0.06
     rộng
    -0.06
    ileri
    -0.06
    SJ
    -0.06
     superheroes
    -0.05
    POSITIVE LOGITS
     ordained
    0.07
    Pl
    0.07
     giám
    0.07
     inv
    0.06
    .kind
    0.06
     GV
    0.06
     contrace
    0.06
     může
    0.06
     dů
    0.06
     componentName
    0.06
    Act Density 0.000%

    No Known Activations