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

    Neuronpedia

    INDEX
    Explanations

    HR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tablets
    -0.07
     browser
    -0.07
    oples
    -0.07
     incidental
    -0.07
    =com
    -0.06
    acias
    -0.06
     अगस
    -0.06
     Mozilla
    -0.06
    todo
    -0.06
    hores
    -0.06
    POSITIVE LOGITS
     dood
    0.07
     educating
    0.06
    UserInfo
    0.06
     kaliteli
    0.06
    월까지
    0.06
     Astro
    0.06
     Dunk
    0.06
    userInfo
    0.05
     eleştir
    0.05
     Attention
    0.05
    Act Density 0.014%

    No Known Activations