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

    Neuronpedia

    INDEX
    Explanations

    bags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ูกค
    -0.07
     الف
    -0.07
    验
    -0.07
    世界
    -0.07
     weighs
    -0.07
     Girl
    -0.06
    一种
    -0.06
     ///
    -0.06
     пл
    -0.06
    ************************
    -0.06
    POSITIVE LOGITS
    myModalLabel
    0.07
    duplicate
    0.06
     Messenger
    0.06
    getApplication
    0.06
     boxShadow
    0.06
    PackageManager
    0.06
    owane
    0.06
     IGN
    0.06
    ammad
    0.06
    bh
    0.06
    Act Density 0.008%

    No Known Activations