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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unks
    -0.07
    VB
    -0.07
     paso
    -0.07
    悰
    -0.06
    _rem
    -0.06
     TOTAL
    -0.06
    ionate
    -0.06
    젼
    -0.06
    serir
    -0.06
    朓
    -0.06
    POSITIVE LOGITS
    不符合
    0.07
     disadvantages
    0.07
    座谈会
    0.07
     קל
    0.06
    ᴼ
    0.06
    /index
    0.06
     McDonald
    0.06
     Ана
    0.06
    ￄ
    0.06
     costs
    0.06
    Act Density 0.016%

    No Known Activations