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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜘蛛词
    -0.07
     Hew
    -0.07
    paused
    -0.06
    _QUERY
    -0.06
    켓
    -0.06
    ереч
    -0.06
    ipated
    -0.06
    endDate
    -0.06
    官网
    -0.06
    표
    -0.06
    POSITIVE LOGITS
     social
    0.07
    NotExist
    0.06
    /Register
    0.06
    ，一
    0.06
    _assignment
    0.06
     veteran
    0.06
     Invite
    0.06
     Education
    0.06
    KS
    0.06
     locally
    0.06
    Act Density 0.000%

    No Known Activations