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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     götür
    -0.07
    OFFSET
    -0.07
    fony
    -0.07
    roducing
    -0.07
     EVENTS
    -0.07
    領導
    -0.07
    红茶
    -0.07
     compromises
    -0.06
    requestData
    -0.06
    pytest
    -0.06
    POSITIVE LOGITS
    客服
    0.08
     Cow
    0.07
     Pros
    0.07
     Scale
    0.07
     signific
    0.07
    二代
    0.07
     Snapshot
    0.06
    )
    0.06
    试管
    0.06
    quals
    0.06
    Act Density 0.504%

    No Known Activations