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

    Neuronpedia

    INDEX
    Explanations

    ্

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encompass
    -0.07
     crosses
    -0.07
    -0.06
     oversees
    -0.06
     surpassed
    -0.06
    ぞ
    -0.06
     altri
    -0.06
     kommer
    -0.06
     incorporated
    -0.06
     anche
    -0.06
    POSITIVE LOGITS
    :params
    0.07
     現
    0.06
    articles
    0.06
    判
    0.06
    旅
    0.06
    elerik
    0.06
     �
    0.06
     �
    0.06
     �
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations