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

    Neuronpedia

    INDEX
    Explanations

    actors as characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caps
    -0.07
     monet
    -0.07
    Publish
    -0.06
     Properties
    -0.06
     Cle
    -0.06
     dq
    -0.06
     SP
    -0.06
     مقدم
    -0.06
     locator
    -0.06
     Spotlight
    -0.06
    POSITIVE LOGITS
     ऐस
    0.07
    เฮ
    0.07
    tvrt
    0.07
     arsenal
    0.07
    toHaveLength
    0.06
    .formData
    0.06
    들의
    0.06
     Lưu
    0.06
     зробити
    0.06
     */
↵
↵
    0.06
    Act Density 0.060%

    No Known Activations