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

    Neuronpedia

    INDEX
    Explanations

    .service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JP
    -0.08
    massage
    -0.07
    貂
    -0.07
     글
    -0.07
    њ
    -0.07
    按摩
    -0.07
     DS
    -0.07
    意义上的
    -0.07
     massage
    -0.07
     bedrooms
    -0.07
    POSITIVE LOGITS
    .Directory
    0.07
    ivy
    0.07
    -pro
    0.07
    打仗
    0.07
    .writ
    0.07
     =
↵
    0.07
    .opensource
    0.07
     analsex
    0.07
    +k
    0.06
     build
    0.06
    Act Density 0.005%

    No Known Activations