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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Посилання
    -0.07
     proyecto
    -0.07
     uniqu
    -0.06
    もしれない
    -0.06
    RFC
    -0.06
     чет
    -0.06
     Θεσσα
    -0.06
     IDR
    -0.06
     sáng
    -0.06
    related
    -0.06
    POSITIVE LOGITS
    ()")↵
    0.07
    φο
    0.07
    \System
    0.07
    acct
    0.07
     Castle
    0.07
    >${
    0.07
    /custom
    0.07
    sol
    0.07
    itness
    0.06
    condition
    0.06
    Act Density 0.003%

    No Known Activations