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

    Neuronpedia

    INDEX
    Explanations

    loans/lending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leth
    -0.07
    ⤑
    -0.07
    GST
    -0.06
     footwear
    -0.06
    早上
    -0.06
     kilomet
    -0.06
    {{$
    -0.06
    輸
    -0.06
     etree
    -0.06
    インド
    -0.06
    POSITIVE LOGITS
     Marvel
    0.08
    谮
    0.07
     הפ
    0.07
    nęła
    0.07
     תפקיד
    0.06
    합니다
    0.06
    Rpc
    0.06
    تصم
    0.06
    潘
    0.06
    ערה
    0.06
    Act Density 0.038%

    No Known Activations