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

    Neuronpedia

    INDEX
    Explanations

    office environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    شارك
    -0.09
    _poly
    -0.08
    /post
    -0.07
    شه
    -0.07
    /history
    -0.07
    Streaming
    -0.07
    ева
    -0.07
    携
    -0.07
    (history
    -0.07
    िज
    -0.07
    POSITIVE LOGITS
     prestig
    0.09
     prestigious
    0.09
     RL
    0.08
     nepot
    0.08
    RL
    0.08
    职位
    0.08
    rent
    0.08
    LDAP
    0.08
     работод
    0.08
    秘书
    0.08
    Act Density 0.002%

    No Known Activations