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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芝加
    -0.08
    aira
    -0.07
    ",-
    -0.07
     vraiment
    -0.07
     Dob
    -0.07
    🔻
    -0.07
     Sour
    -0.07
     FORE
    -0.07
    DOG
    -0.07
     continuous
    -0.07
    POSITIVE LOGITS
    可靠性
    0.07
    ┞
    0.07
     Ruby
    0.06
     slipping
    0.06
    depth
    0.06
    similar
    0.06
     товаров
    0.06
     האמר
    0.06
     evidenced
    0.06
    NotEmpty
    0.06
    Act Density 0.196%

    No Known Activations