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

    Neuronpedia

    INDEX
    Explanations

    Beginning of proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .have
    -0.06
    pipes
    -0.06
    _tweets
    -0.06
    -down
    -0.06
     intr
    -0.06
    🍲
    -0.06
    terms
    -0.06
    ��
    -0.06
    ")]↵↵
    -0.06
     For
    -0.06
    POSITIVE LOGITS
    .engine
    0.07
    際
    0.07
    .getParam
    0.07
     itemList
    0.07
    キャッシング
    0.07
     awkward
    0.07
    .showMessage
    0.07
    getStringExtra
    0.07
     glEnable
    0.07
     смож
    0.06
    Act Density 0.593%

    No Known Activations