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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Breed
    -0.07
    kids
    -0.06
    คาส
    -0.06
    시간
    -0.06
     HAND
    -0.06
    只能
    -0.06
    经理
    -0.06
    Sharing
    -0.06
    yard
    -0.06
    егра
    -0.06
    POSITIVE LOGITS
    -translate
    0.07
    /client
    0.07
     В
    0.07
     Wen
    0.06
    LK
    0.06
     perspectives
    0.06
     rewritten
    0.06
     superclass
    0.06
     topical
    0.06
    Digite
    0.06
    Act Density 0.000%

    No Known Activations