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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Abstract
    -0.07
    agment
    -0.06
     Ст
    -0.06
    Presence
    -0.06
    ità
    -0.06
     Bach
    -0.06
    Letters
    -0.06
     permet
    -0.06
    unct
    -0.06
    usa
    -0.06
    POSITIVE LOGITS
     machining
    0.07
     엔
    0.06
    ="",
    0.06
     сбор
    0.06
     reasoning
    0.06
    =:
    0.06
     darling
    0.06
     completionHandler
    0.06
    hog
    0.06
    股份有限公司
    0.06
    Act Density 0.050%

    No Known Activations