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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쫑
    -0.07
    琐
    -0.07
    ombs
    -0.07
    终身
    -0.07
     Chapter
    -0.07
     BSD
    -0.06
    ずに
    -0.06
    CHKERRQ
    -0.06
     أجل
    -0.06
    每个月
    -0.06
    POSITIVE LOGITS
    Delivery
    0.08
     fundraiser
    0.08
    ﲰ
    0.07
    _supported
    0.07
    avenport
    0.07
     eater
    0.07
     scraper
    0.07
     vegan
    0.07
    夔
    0.07
    海边
    0.07
    Act Density 0.005%

    No Known Activations