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

    Neuronpedia

    INDEX
    Explanations

    job-related experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _effects
    -0.07
     wishing
    -0.07
    lient
    -0.07
    𝖑
    -0.07
     UserRole
    -0.07
    𝚛
    -0.07
    лер
    -0.07
     DEST
    -0.07
    Ղ
    -0.07
     Hil
    -0.07
    POSITIVE LOGITS
    脾胃
    0.08
    尸
    0.07
     cortex
    0.07
     сраз
    0.07
    ◪
    0.07
    обще
    0.07
    的前提下
    0.06
    核心区
    0.06
    禁区
    0.06
    setParameter
    0.06
    Act Density 0.101%

    No Known Activations