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

    Neuronpedia

    INDEX
    Explanations

    browser

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fh
    -0.07
    螨
    -0.07
     종
    -0.07
    �
    -0.07
    ):↵
    -0.07
    ={}↵
    -0.06
    _requires
    -0.06
     там
    -0.06
    枇
    -0.06
    藟
    -0.06
    POSITIVE LOGITS
     goal
    0.08
    Driven
    0.07
    logic
    0.07
    skin
    0.07
     Goals
    0.07
     jobId
    0.07
    couldn
    0.07
    转型发展
    0.07
    ylan
    0.07
     goals
    0.06
    Act Density 0.001%

    No Known Activations