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

    Neuronpedia

    INDEX
    Explanations

    deform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equ
    -0.08
     pure
    -0.07
     Saudi
    -0.07
     Pa
    -0.07
     IE
    -0.07
    airo
    -0.07
    隐约
    -0.07
    קצב
    -0.07
     muj
    -0.07
     Int
    -0.07
    POSITIVE LOGITS
    ladığı
    0.07
    尊
    0.07
    分布式
    0.07
    pagina
    0.07
    etas
    0.07
     maduras
    0.07
    aran
    0.07
    AN
    0.06
     PropertyInfo
    0.06
     Herman
    0.06
    Act Density 0.030%

    No Known Activations