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

    Neuronpedia

    INDEX
    Explanations

    Board

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auty
    -0.07
     Fixture
    -0.07
     FontWeight
    -0.07
     لأ
    -0.07
    >'
↵
    -0.07
    عار
    -0.07
    Guest
    -0.07
    ❖
    -0.07
     Restrictions
    -0.07
        
    -0.07
    POSITIVE LOGITS
    _like
    0.07
     też
    0.06
    逻辑
    0.06
    wró
    0.06
    up
    0.06
    碛
    0.06
    感覺
    0.06
     clear
    0.06
    hec
    0.06
     mau
    0.06
    Act Density 0.170%

    No Known Activations