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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lighthouse
    -0.08
     Nutrition
    -0.07
     nutrition
    -0.07
     лог
    -0.07
     Rider
    -0.07
     অ্য
    -0.07
    _catalog
    -0.07
     entren
    -0.07
     Hampshire
    -0.07
     separately
    -0.07
    POSITIVE LOGITS
    つまり
    0.08
    。因此
    0.08
     즉
    0.08
    �
    0.08
    rance
    0.07
    治
    0.07
    arget
    0.07
     यानी
    0.07
    地下
    0.07
    dq
    0.07
    Act Density 0.164%

    No Known Activations